Skip to content
Public template

About

♾️ TRANSFORMATIONAL META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡ → Out-Evolve ♾️

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

310 stars

Watchers

10 watching

Forks

Latest commit

 

History

10,604 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Two lists. A clear next step.

Try it now → · Essayer maintenant →

Compare two nonpersonal CSV lists locally, see missing matches and conflicting values, and group every exception into an action plan without losing its source references. Download the plan, full differences and an offline reusable workspace. No account, installation, wallet, API key or model service. Grouping measures records and evidence coverage; it does not establish time saved or decide which source is correct. Foundation: Transformational Intelligence · Implementation and acceptance.

Find your Alpha. Build your SUCCESSOR Ω.

MONTREAL.AI FLAGSHIP · Computer Use · Level 3 strategy development · Level 4 problem reframing

Find a valuable opportunity in software, research or mathematics. Use Computer Use to investigate real public material and produce a concrete work product. Develop competing strategies, combine what works, and challenge problem formulations that unnecessarily limit the outcome. Keep the attempts, evidence and lessons in one project.

Start the flagship → · Démarrer le parcours phare →

Planning and the catalog example are free in your browser. Computer execution uses a separately configured native model and isolated runner. What works now and how to begin.

Autonomous Enterprises · Build the means of building. Construct checked Walsh, XOR-convolution and inverse capabilities, freeze their bytes, then invoke them on later tasks in the same mission history. Free local foundry and evidence guide · Selected 23-page paper · Source candidate and qualification. This additive source preview preserves SUCCESSOR Ω, Discovery Lab and all six research stages. Installed cross-repository receivers, public deployment and the operational real-task pilot remain unqualified.

Foundation: AGI ALPHA

A Scalable Substrate for Intelligence Organizations

AGI ALPHA organizes intelligence. TRANSFORMATIONAL INTELLIGENCE changes the conditions of discovery. The AGI ALPHA paper proposes a testable architecture and evaluation program for coordinated, governed, evidence-producing work across agents, jobs, validators, tools, memory, markets, settlement and capacity allocation. It does not claim achieved AGI, ASI, empirical state of the art, autonomous sovereignty, energy abundance or civilization-scale capability.

Read the foundational AGI ALPHA paper → · Announcement on X · TRANSFORMATIONAL INTELLIGENCE and the research series

Related architecture research

Mission-Sovereign Successor · v5.0.0

A proposed design for governed mission capability: manufacture useful capability, require fresh proof for mission-bounded superiority, and keep authority within that proof. A research doctrine, not a report of achieved general capability or deployed mission sovereignty.

Read Mission-Sovereign Successor (v5.0.0 PDF) → · Paper announcement on X

NEURAL-SYMBOLIC SUCCESSOR Ω

Customer-Owned Mission Intelligence · Current edition: v1

A proposed portable mission institution with four distinct programs: WORLD maintains beliefs, POLICY proposes actions, PROOF records independently demonstrated claims, and AUTHORITY defines permitted actions. A successor may inherit memory, provenance, failures, program lineage and operating history, but proof status and production authority start empty and must be earned anew. Architecture and product constitution, not a claim of complete implementation or achieved general autonomous capability.

Read the current architecture paper (v1 PDF) → · v1 announcement on X · Earlier edition (v0 PDF) · v0 announcement

SUCCESSOR Ω × AGI JOBS

A proposed connection between mission-governed intelligence and sealed work orders that manufacture, test, operate and renew capabilities. The paper connects institutional design with a work-order mechanism; it does not establish a fully deployed or commercially proven autonomous institution.

Read SUCCESSOR Ω × AGI JOBS (v2 PDF) → · Paper announcement on X

Gym, Specialist ASI & Successor Ω

A proposed institutional separation: Mission Gym supplies controlled, versioned, rights-cleared mission environments; Specialist ASI is an earned, mission-bounded designation requiring comparison against strong alternatives on fresh protected work; Successor Ω requires separate admission with scoped, expiring, revocable authority. Training is not certification, and descendants may inherit memory, not authority. These are research design requirements, not a claim that the designation or deployed institution has been achieved.

Read Gym, Specialist ASI & Successor Ω (v2.1.0 PDF) → · Paper announcement on X

Featured thread from MONTREAL.AI →

Featured research

Learning to Change the Game

Identify restrictive problem formulations, construct better ones and test that they still serve the intended purpose. A framework for independently testable reformulation, not just better search. Vincent Boucher · MONTREAL.AI · 2026-10 · English PDF.

Companion papers · reading order

  • Autonomous Enterprises — Build the Means of Building · A bounded certifying computation constructs a checked transform–convolution–inverse solver and studies exact capital and capability retention under declared concatenability assumptions. The finite examples compare shared construction with isolated tasks and show when cash-only pruning loses useful capability. Research constructions and exact models, not a new Fourier algorithm, physical deployment or realized commercial growth. Vincent Boucher · MONTREAL.AI · 2026-10-21 · English PDF.
  • Autonomous Enterprises — Activate. Evolve. Scale. · Three deterministic local offerings study reusable launch kits and transfer of rejection experience while leaving full acceptance checks unchanged. Retained limits include a conventional ordering that wins one comparison, a rejected second learned update and a four-worker run slower than two workers. A bounded local study, not general recursive self-improvement or evidence of three paying businesses. Vincent Boucher · MONTREAL.AI · QUEBEC.AI · 2026-10-22 · English PDF.
  • Autonomous Enterprises — SUCCESSOR Ω Harness · A source-grounded integration specification and bounded interval-measurement experiment compare independent setup, ordinary harness reuse and instrument reuse, including verification, failed transfer and recovery. The manuscript distinguishes deployed inventory, an open Harness candidate, replayed examples and new simulations. It does not establish autonomous incorporation, observed demand, investment performance or approved mainnet execution. The Harness implementation remains separately tracked in unresolved PR #4863; this paper listing does not claim that it has shipped. Vincent Boucher · MONTREAL.AI · QUEBEC.AI · 2026-10-22 · English PDF.
  • Autonomous Enterprises — Foundry v2 · A simulated thermal-fluid foundry constructs fixtures, a calibration station and a qualified research instrument, then a new calorimetry method and a distinct simulated successor. A retained failure: the 4.9477% predicted/observed heat difference passes the 5% runtime rule, while the calorimeter has 8.6964% error against reference-model true heat. Conventional engineering ties useful accuracy with 384 versus 672 readings; a centralized lab is CAD 460 cheaper. Participant withdrawal and underutilization fail in the tested economic cases. Finite search, modeled economics and Python contract checks; physical construction and deployment NOT RUN. Reproduction requires the full research companion; standalone TeX requires the full LaTeX source ZIP. Vincent Boucher · MONTREAL.AI · QUEBEC.AI · Montréal, Québec, Canada · 2026-10-22 · English PDF. Read the edition and resources · Explore the interactive foundry · Download the research companion · View source and evidence
  • Autonomous Enterprises — Capability Inheritance · Retained executable capabilities serve 48 mathematical tasks using 63,196 counted work units versus 915,136 for rebuilding, but the supplied expert uses 5,760. Inherited successor qualification loses 7,918 versus 2,030 directly. A separate simulated thermal witness gives a conditional 1.8862% bound. Local-EVM and native-worker evidence remains separate from unfinished end-to-end thermal integration; physical validity and full monetary, human and energy costs are unknown. No measured profit is established. The 25-page manuscript is preserved; reproducible TeX requires its complete source package. Vincent Boucher · MONTREAL.AI · 2026-10-22 · English PDF. Read the edition and resources
  • Autonomous Enterprises — The Discoverability Compiler · A bounded compiler constructs nuisance-canceling measurement programs and checks whether they separate an authorized decision. Conventional baselines tie development acquisition costs; an adaptive control wins. Reuse reduces counted construction work, while timing is unstable and centralized execution remains faster. The ≤US$100 total-cost to US$10,000 realizable incremental-value challenge is UNPROVEN: no executable offer or customer receipt exists, and complete cost is unknown. This preserved 24-page amended paper does not qualify its open-review runnable experience or establish physical validation or installed enterprise integration. Reproducible TeX requires the complete research source. Vincent Boucher · MONTREAL.AI · QUEBEC.AI · 2026-10-22 · English PDF. Read the edition and resources
  • Out-Learn 📚 · Studies how to construct measurement protocols and learn reusable calibration, with error guarantees under declared drift and measurement-error assumptions in exact synthetic studies. Vincent Boucher · MONTREAL.AI · 2026-10-21 · English PDF.
  • Out-Think 🧠 · Studies executable reasoning representations that preserve required answers and operations, and when to replace rather than refine inherited internal codes, in exact finite models. Vincent Boucher · MONTREAL.AI · 2026-10-21 · English PDF.
  • Out-Design 🎨 · Studies equivalent implementations that preserve required services and release usable capacity for reconfiguration and new capabilities, with checked constructions in finite executable models. Vincent Boucher · MONTREAL.AI · 2026-10-21 · English PDF.
  • Out-Strategise ♟️ · Couple observation with construction to create strategies that achieve the required outcome despite unresolved uncertainty. Vincent Boucher · MONTREAL.AI · 2026-10-20 · English PDF.
  • Out-Execute ⚡ · Preserve progress as tasks change through reusable execution capabilities and independently checked boundary contracts, demonstrated in finite synthetic studies. Vincent Boucher · MONTREAL.AI · 2026-10-21 · English PDF.
  • Out-Evolve ♾️ · A proposed architecture for building experimentation and production capabilities that make further discoveries and successor capabilities possible. Vincent Boucher · MONTREAL.AI · 2026-10-20 · English PDF.
  • TRANSFORMATIONAL AUTONOMOUS ENTERPRISES · A finite graph-capability study connects four source runtimes and five local-EVM contracts: fresh mission checks remain, repeated qualification work falls, direct-specialist wins and unproven economic value are retained. The experimental companion's source and assembly guidance do not establish installed or deployed acceptance. MONTREAL.AI — Writer #4 research edition · 2026-10-23 · English PDF. Download standalone TeX · Current corrected companion guide and helper · Historical experimental companion source and assembly
  • The Possibility Foundry · A bounded 64-channel synthetic-spectroscopy study constructs a calibrated instrument from a finite 60-plan grammar. Under the declared resource cap, 1,678/2,048 fresh missions pass quality and cost. The full scanner has better quality; both supplied software builders use less construction work than the foundry. Transfer succeeds on 204/512 tasks; narrow-line stress passes 0/128. A temporal child passes 128/128 with retained parent capital, but 0/128 with fully loaded de novo cost; a shorter conventional construction also fits its cap. Two same-seed runs are not independent replication. Retained Alpha workbench/Jobs compiler source evidence does not establish installed four-repository, physical or commercial acceptance. Full monetary and human costs are unknown; the $100-to-$10,000 target is NOT ESTABLISHED. This original 21-page paper is preserved; compiling its TeX requires the complete archive bibliography and figures. MONTREAL.AI; research direction Vincent Boucher · 2026-10-23 · English PDF. Download complete research source ZIP · Download visual signature (not cryptographic) · View source and evidence
  • SUCCESSOR Ω HARNESS · A 28-page simulated detector study with a runnable research companion: retained construction ties conventional caching, while expert construction uses fewer counted rational calls. Physical validity, settlement and profit are not established. MONTREAL.AI · AGI ALPHA Research & Engineering · 2026-10-24 · English PDF. Download the research companion · Download complete research source ZIP · View source and evidence
  • AGI ALPHA FLYWHEEL · An 18-page bounded study of retained executable component bases. All four workflows qualify 864/864 tasks; conventional caching ties the flywheel, the authored expert costs less, and none of eight streams demonstrates sustained acceleration. Computational counts do not establish commercial value. Vincent Boucher · MONTREAL.AI · 2026-10-24 · English PDF.
  • AGI ALPHA FLYWHEEL: The Economics of Autonomous Work · A bounded exact-reconciliation study reports 36/36 accepted fresh jobs and 0.301-second median turnaround. Official labor data support conditional human-work economics; complete costs, remaining employer attention and a matched human trial are unmeasured. Vincent Boucher · MONTREAL.AI · 2026-10-25 · English PDF. Historical experimental companion source and assembly
  • AGI ALPHA FLYWHEEL · A preregistered bounded study accepts 42/42 fresh jobs across seven digital-work families and records actual reusable-capability invocation. Tested inheritance candidates establish neither net savings nor self-acceleration. Official labor data support conditional adoption economics; full Agent cost and employer attention remain unmeasured. AGI ALPHA research engineering study · 2026-10-25 · English PDF. Historical experimental companion source and assembly
  • AGI ALPHA FLYWHEEL · A separately frozen, market-data-grounded operational comparison prices delivery, failures, review, setup and capability upkeep against traditional non-AI work. The primary 30-minute office scenario does not establish an economic win at the modeled expected-use capacity limit. Conditional thresholds, complete-demand fallback and unvalidated setup scheduling remain explicit; no deployed-service cost or new human trial is claimed. AGI ALPHA research engineering study · 2026-10-25 · English PDF. Historical experimental companion source and assembly
  • AGI ALPHA FLYWHEEL: The Productive Capital Engine · A frozen study connects useful local work to a conserved economic model; conditional service margins are modeled, while the constructed child does not outperform conventional reuse. MONTREAL.AI · Independent research edition · 2026-10-25 · English PDF.
  • AGI ALPHA FLYWHEEL · A separately preregistered financial simulation connects useful recorded work, complete business costs, collected proceeds, reserves and bounded capability investment. It preserves unfavorable paths, idle allocations and failed construction, with distinct source-inspected USDC and AGIALPHA settlement routes. Simulated gains, token realization and customer value remain conditional; no live revenue, transaction or self-acceleration is demonstrated. AGI ALPHA research engineering study · 2026-10-25 · English PDF. Historical experimental companion source and assembly
  • BUILD THE NEXT ADVANTAGE · Example-derived quote adapters qualify on 96 fresh missions. Active selection matches the learned recipe and LLM-assisted constructor; complete costs and simulated financing keep the stronger incumbent and expose the limits. Vincent Boucher · MONTREAL.AI · 2026-10-25 · English PDF.
  • AGI ALPHA FLYWHEEL: The Autonomous Work Economy · An independent bounded study delivers 16 local artifacts across four workflow families, retains eight expected refusals, and tests a successor on eight later quote cases. Complete costs and reinvestment remain conditional models; customer payments, full authenticated execution and self-acceleration are not established. Vincent Boucher · MONTREAL.AI · 2026-10-25 · English PDF.
  • THE ADVANTAGE THAT FUNDS THE NEXT · A versioned release-inventory intake capability serves the actual Alpha Workbench. Three strong methods correctly complete 16 fresh comparison requests and 64 representations each. Complete costs and attention savings remain unmeasured; no material incremental advantage is established. Financing scenarios bind the exact tested asset, preserve adverse outcomes and leave actual economic admission on HOLD. AGI ALPHA research engineering study · 2026-10-25 · English PDF. Historical experimental companion source and assembly
  • Build an Advantage That Repays Its Cost — The Investment Gate · Nine scoped internal requests and eighteen evaluations with overlapping inputs produced eight complete measured local paths, not eight authenticated native missions. One scope retained its native artifact-policy refusal. No productive asset was selected or constructed and no untouched confirmation trial was run. Full monetary cost, repayment and positive incremental economics remain unestablished. DISCOVERY/HOLD. AGI ALPHA Research · MONTREAL.AI · 2026-10-25 · English PDF.
  • The Next Upgrade · A consumer-specific dependency assessment accepted nine of twelve custom-method scopes versus twelve of twelve for the conventional comparator. The custom method was rejected; local task support and reuse do not establish cheaper capability construction or commercial success. Complete monetary costs, repayment and sustained acceleration remain unestablished. Economic HOLD. AGI ALPHA Research · 2026-10-26 · English PDF. Historical experimental companion source and assembly
  • Profitable Work First. Compounding Capability When Worthwhile. · Under declared assumptions, a simulated coordination-mechanism foundry produces positive mean Beta-only surplus, including a stricter useful-receipt-only sensitivity. These are conditional model results, not actual customer sales or qualified frontier-model delivery. Primary confirmation does not establish a positive additional enterprise benefit from retained Alpha or network sharing; capability compounding remains unproven. Independent AI-assisted research edition prepared for MONTREAL.AI · 2026-10-26 · English PDF. Historical experimental companion source and assembly
  • When Paid Work Teaches the Network · Competent Beta is profitable under the modeled primary markets, with incomplete service-quality qualification. Selected retention policies keep nothing; a cheaper-retention diagnostic supports useful peer reuse but remains uneconomic as a complete program. This is not demonstrated profitable autonomy or a positive network flywheel. Prepared for Vincent Boucher / MONTREAL.AI; research execution and manuscript prepared with ChatGPT · 2026-10-27 · English PDF. Read the edition and resources
  • AGI ALPHA FLYWHEEL — The Network That Learns to Invent · A numerical learning system constructed by the research team develops a reduced basis from thermal work and tests its transfer to fresh diffusion and sensor-design missions. Mean raw transfer error falls 26.3-fold, but neither raw version passes any of 64 recipient cases; corrected solutions pass. The competent generalist matches the composition’s identification success. Under explicit cost and demand assumptions, modeled Beta delivery can be profitable while optional retention is rejected. Local numerical evidence and simulated economics, not customer sales, autonomous invention, live ENS authentication or specialist superintelligence. Vincent Boucher · President of MONTREAL.AI · 2026-10-27 · English PDF. Read the edition and resources · Historical experimental companion source and assembly · Download complete research source ZIP · View source and evidence
  • The Enterprise That Invents Its Next Advantage · Versioned offerings and bounded enterprise decisions connect to the existing executor, optional Gym, protected capabilities and A/B/C ledger. A finite internal artifact and twelve fresh checks execute; admission is rejected, funds are held and an adjacent offering remains a hypothesis. A separate fictional-authority relay tests protected invocation. No live frontier advantage, actual revenue or complete-cost profit is established. Vincent Boucher · President of MONTREAL.AI · 2026-10-27 · English PDF.
  • The Enterprise That Invents Its Next Advantage · Corrected Edition · Corrected implementation edition: dispatch rechecks every decision and offering evidence reference; interrupted launch finalization recovers only from the exact terminal failed receipt and complete accounting. Versioned offerings, bounded decisions, twelve fresh finite cases and fictional protected relay remain inspectable. Admission is rejected, funds held and adjacent demand unmeasured. No live Alpha, customer revenue or complete-cost profit established. Vincent Boucher · President of MONTREAL.AI · 2026-10-27 · English PDF.
  • The Enterprise That Invents Its Next Advantage · Production Evidence Edition · Current implementation edition checks commercial evidence when authorizing an offering, selecting production and dispatching a mission. Withdrawn forecasts lead to holding funds and block previously selected work. The connected technical relay remains a bounded hybrid study: twelve fresh finite checks, rejected Alpha admission, a hypothetical adjacent offering and explicitly fictional peer authority. No actual customer revenue or complete-cost profit is established. Vincent Boucher · President of MONTREAL.AI · 2026-10-27 · English PDF.
  • The Enterprise That Invents Its Next Advantage · Capacity Evidence Edition · Current implementation separates per-offering occupied slots from the enterprise global ceiling, keeps production bound to current commercial evidence and preserves intent-bound failure recovery. Two-offering and withdrawal regressions complement the connected internal placement/Gym/protected-relay study. Twelve fresh finite checks pass; Alpha admission is rejected and funds held. No actual customer revenue, complete-cost profit or growing network advantage is established. Vincent Boucher · President of MONTREAL.AI · 2026-10-27 · English PDF.
  • AGI ALPHA FLYWHEEL — From Verified Criticism to Executable Repair · Reader 1 · A bounded corrective-constraint compiler accepts 36/36 modeled schedules; the complete conventional LP also accepts 36/36 with lower measured deployment compute. The recovered instrument ledger records −8.574947 SIM USD operating profit and zero unrestricted earned funds. Exploratory software and simulated accounts do not establish a real same-cohort profit crossing, learning advantage, hostile-program isolation or a completed invention flywheel. Vincent Boucher · President of MONTREAL.AI · 2026-10-29 · English PDF. Historical experimental companion source and assembly

Research proposals and bounded studies, not claims of general autonomous capability or physical deployment. Explore the papers in English or French

Current experimental source candidate · 1.47.0. Connected discovery and operating boundaries. Exact approved paper readers. Protected Flywheel operating boundaries. Additive Flywheel flagship. Explore the public simulation. Checked planning and repair. Configure the bounded Strategy Succession executor. Published 1.43 remains preserved. The existing alpha-agent successor-study entry point can run an explicitly approved finite operation, retain a closed executable source-selection program and test it on later changed inputs. Pause/Stop, lease expiry, bounded retries and committed-child recovery keep their existing journal history. The installed study tied equally enabled conventional reuse; capability growth and self-acceleration remain unestablished. Operating guide. The published 1.42.0 browser-first catalogue guide is preserved. Preserves the immutable workbench submission patch. The existing research catalogue now connects the Foundry v2 paper, retained-evidence interactive experience, named reproducible companion and source release. The inherited enterprise workspace develops a bounded finite capability, freezes it and compares later tasks while retaining rejected alternatives, declared costs and history. Finite synthetic studies and zero-cap inspection drafts describe this preview; physical construction, installed enterprise compatibility, external model/tool pilots and observed organizational benefit retain separate qualification. The corrected companion retains its non-UI source-API/local-EVM evidence and its full HTTP QA gate. The 1.41.0 standalone publication and 1.41.1 immutable submissions remain preserved. This 1.42.0 guide adds local catalogue usability; its own exact-source release and public browser gates remain required.

This combined software candidate adds bounded OUT-EXECUTE execution to the preserved proposal and Out-Evolve journeys. This is not a claim that every proposed capability is implemented. Synthetic results and unsigned work drafts grant no operational authority.

Choose your next step

Open the guided website → · Commencer en français →

Your goal Start here
Investigate a valuable digital-work opportunity, software bottleneck, research question or mathematical problem Find your Alpha. Build your SUCCESSOR Ω. · Guide
Inspect a maintained local engineering example Catalog reconciliation example · Scope and reproduction
Find your Alpha and retain one project through Jobs / Fleet Discovery → Guided project history
Explore a free example with no account or installation Guided first plan
Create useful files and retain a personal SUCCESSOR Ω Five work families
Prepare, protect and continue a project Nova-Seed Studio
Commission USDC work or prepare a worker computer AGIJobManager · Fleet setup
Explore the AGI Jobs demos and $AGIALPHA contract ecosystem AGI Jobs v0 · Deployment directory
Install the native agent Published downloads and evidence · Operator guide

Browser preparation is free. Execution, participant review and settlement require their own configuration and approval. AGIJobManager settles in USDC; the Alpha / Jobs v0 contracts use $AGIALPHA. Source versions and published downloads can differ: use the evidence and instructions supplied with your chosen release.

New Ethereum Mainnet deployment, October 18, 2026: five contract addresses and verified graph. Publication records the deployment; operating approval remains separate. These five current records are separate from the older 29-address ecosystem snapshots below. Existing wallet profiles retain their pinned historical addresses; publication does not migrate them.

Current contribution policy: Local pre-commit checks are recommended feedback, not a prerequisite for opening a draft or pull request. Disclose failed or unrun checks and their reason; do not claim a pass. This current policy supersedes historical local-hook submission prerequisites in the preserved guide below. Installed hooks, access restrictions and required hosted merge/release checks are unchanged and not waived. See Contributing and agent guidance.

Find a valuable opportunity. Invent a better approach. Build what matters. → Start with a real software improvement, an evidence-based research question or a rigorous mathematical investigation. Produce a source-grounded artifact, design tests for competing approaches, and consider whether a different formulation creates more value. Code proposals need execution; mathematical claims need proof review. The configured browser runner retains observed work for your review. English / Français guide and reproduction.

Current source candidate · 1.37.0. Start here · Release notes · Release evidence and supported scope. Version 1.37.0 adds the capability workspace and bounded Out-Evolve constructor, independent checking, frozen reuse and retained successor histories. These are synthetic software mechanisms, not physical deployment or general invention. Published v1.36.0 and its source-bound artifacts remain unchanged; they do not contain these later additions. Exact-source 1.37.0 release qualification and Jobs/Fleet compatibility remain separate gates. Use matching published assets from Releases; a source label or feature merge alone is not publication.

Find your Alpha. Build your SUCCESSOR Ω. · Computer Use expansion. Define a useful outcome, prepare screenshot-and-keyboard/mouse work, and retain its results in the same project. Level 3: discover, test, combine and improve strategies. Level 4: challenge an unnecessary restriction and test a different problem formulation while preserving the required outcome and acceptance criteria. Browser preparation makes no model call. Execution uses the separately configured native model and isolated Chromium runner; imports retain historical observations and your review, with no inherited authority. The exact release manifest and acceptance evidence identify delivery. This addition is absent from v1.34.0; live-model task qualification and independent review remain separate from software publication. English / Français journey and current limits.

Current Cross-Industry supplied-input journey

The original project narrative and historical quick-start below are preserved for context. For the supported local comparison, use this current guide; historical deployment commands are unqualified advanced material and are not required for the supplied-input journey.

In an installed Alpha environment, inspect the explicit synthetic example:

python -m alpha_factory_v1.demos.cross_industry_alpha_factory.opportunity_comparison --example

Then supply your own bounded assessment JSON with --input FILE and inspect the ranking, exclusions, evidence and Pareto trade-offs. The notebook walkthrough executes local comparison and recoverable evidence export; it does not start cloud tunnels, upload endpoints, training or providers. Legacy deployment scripts remain unqualified advanced material, not prerequisites for this verified comparison.

Create a useful SUCCESSOR Ω → Five bounded work families · English / Français · Real artifacts you can retain · Optional native Computer Use. Scope, setup and reproduction.

Useful work. Recovered. Reused. — Read the computer-use study. Two repaired websites, 19/19 recovery checks and 21.4% fewer scripted setup controls. Simulated owner; real software checks. Not a production benchmark or measured human time saving. English / Français visual reader · Public report pack · Recorded results.

Build your own SUCCESSOR Ω with Alpha Agent + AGI Jobs → Name your mission, run four candidate programs, compile 21 bounded job drafts, and keep the working lab offline. English / Français · Large text · No account, wallet or installation. Source and reproduction guide · Version 1.28.0. The example runs both projects’ code locally. Independent proof remains absent; admission stays on HOLD.

Take home your own SUCCESSOR Ω. Create your personal lab. Give it a name, run real experiments, then save the whole working lab as one file. Reopen it offline, try new challenges and keep your discoveries. Free, English/French, larger text, no account or installation. Personal lab guide · What is new in 1.27.2.

Ideas behind your SUCCESSOR Ω

Read four selected essays on governed improvement, sustainable capabilities, invention and retained work history. English/French summaries connect each essay to a current guide. Reading notes and version context.

Alpha Agent + AGI Jobs: from a useful idea to accepted work

Alpha helps produce the work; AGI Jobs supplies rules for commissioning, reviewing and settling it. Together, they offer the building blocks for a traceable work cycle: define a worthwhile task, produce a result, check the evidence, settle according to agreed terms, and retain what proved useful. Alpha's deployed Ascension suite also provides plan records, campaign funding and spending constrained to committed jobs in its own market. A connected AGI Jobs workflow requires explicit configuration and commissioning.

Shared token · Ethereum mainnet · $AGIALPHA · 18 decimals

0xA61a3B3a130a9c20768EEBF97E21515A6046a1fA

Explore the visual connection guide and its 29-instance historical inventory · Français · Practical workflow and operating boundaries · AGI Jobs companion guide

The public records identify 5 Alpha Ascension contracts deployed on 11 October 2026 and 24 AGI Jobs contract instances inventoried on 12 October 2026, including its coordinator and 10 fixed implementation contracts. Both records name the token above; it is a shared dependency, not another suite instance. Alpha deployment evidence · AGI Jobs deployment evidence.

These dated records establish deployment, not a commissioned joint service. The Alpha deployment predates newer settlement safeguards; its MARK treasury targets its own fixed market. The Jobs record does not approve production or open live intake. Check the Alpha deployment guide and current Jobs readiness guide before live use. Exploring the guide and personal lab is free.

Prefer a simple planner? Make your first plan. Choose what matters, review a simple plan and keep a readable copy. No technical experience, account, wallet, payment or installation is needed. Visit the welcoming homepage · Français · Larger text · Simple guide · 1.26.3 release notes.

Contract maintenance · Version 1.28.1. Follow the warning and verification guide to distinguish source compilation, explorer verification and the immutable October 11 deployment.

Historical Ethereum mainnet deployment · 11 October 2026. Five contracts and the completed on-chain ownership handoff are recorded. Etherscan source verification and Ledger custody are operator-reported; the public archive does not include the Etherscan API transcript. Addresses, owner guide and read-only verification. The deployed contracts predate the current settlement fixes; resolve that difference before admissions or funding.

SUCCESSOR Ω — 1.24.1. Build and examine a bounded mission capability, retain useful knowledge and require every successor to earn new proof and permission. Bilingual mission workspace · Quickstart and operator guide · Architecture and boundaries · Release notes and acceptance requirements. Local rehearsal is not independent qualification or production authority. Existing missions, research and flowcharts remain available.

Choose a current launch path: useful Alpha flagship, existing browser laboratory, minimal native installation, operator recovery and upgrades, or Hardhat deployment and migration guide. The repository guide explains which dependencies each path needs. Publication requires the exact-commit acceptance workflow; use the matching published release assets and manifest.

Current contract configuration: Solidity reference contracts pin the canonical $AGIALPHA address 0xa61a3b3a130a9c20768eebf97e21515a6046a1fa and 18 decimals. Environment variables do not override those Solidity constants. The historical alternate-network override instruction retained below is superseded by the current contract guide. Its local fixture is disposable and does not deploy to an external chain, migrate real tokens or establish production authority.

1.23.3 — Safer repairs and clearer browser workflows. Start with a useful result · Find your way around the repository · Release notes. Responsive Insight panels, refreshed browser dependencies, reliable MuZero controls and safer file-preserving repairs. Original content and flowcharts remain preserved.

1.23.1 — Complete demo catalog and repeatable evidence. Discover all 26 entries and retain each experiment with alpha-factory demo run <demo> --new-run. Walkthrough · Release notes. All original demos and flowcharts remain.

1.22.1 — Sovereign session cleanup. Locking clears imported drafts and review notes, retains saved mandates, and isolates delayed requests from the next session. Release notes.

1.22.0 — Sovereign Workbench. Run a bounded portfolio, schedule and evidence workflow with explicit reviews, a private signed journal and verifiable exports. Start here · Release notes. Original source, presentation and diagrams remain preserved.

1.21.0 — Finance Alpha research terminal. Audit cash, costs, next-open fills and risk decisions in a local, reproducible paper experiment. Start here · Release notes. Original diagrams and research remain preserved.

1.20.1 — Planning lab reliability. Download reproducible reports, recover cleanly from failed runs, and follow corrected platform setup. Lab guide · Release notes. Existing flowcharts and research are preserved.

1.20.0 — Evidence & Planning Lab. Cited task evidence, optional local-model advice, trained MuZero search and measured action traces. Start the lab · Release notes. Original presentation and research preserved.

1.19.0 — MuZero Planning Lab. Train a small neural world model, inspect reward-aware tree search and compare measured baselines. Start the lab · Release notes. Original flowcharts and research remain preserved.

1.18.0 — Meta-Agentic AGI v3 Curriculum Lab. Generate tasks, evolve bounded solvers, inspect lineage and independently review the frozen candidate. Open the lab · Operating guide. Original flowcharts and research are preserved.

Version 1.17.0 adds the MATS Search Lab. Explore branching workflow designs, inspect every rollout, audit the search gap, and challenge a frozen candidate against five independent model gates. Open the lab · Guide · Release notes. Original diagrams, notebooks and research remain available in the preserved archive.

Version 1.16.0 adds the Experience Learning Lab. Act, observe, learn, and challenge a frozen candidate with reproducible outcomes and independent review gates. Open the lab · Guide · Release notes.

Version 1.15.0 adds the Insight Discovery Workbench. Review cross-sector hypotheses, inspect source assumptions, allocate review time and export reproducible dossiers, verification jobs and plaintext Nova-Seed drafts. Open the workbench · Guide · Release notes. Original research, diagrams and launchers remain available.

Version 1.14.0 adds a complete Governance Workbench. Review a proposal, inspect nine conditional gates, challenge adversarial cases, and export reproducible evidence with input-bound validator jobs. The original manuscripts, diagrams, simulator and research presentation remain available. Operating guide · Release notes.

Version 1.13.1 brings Business 3's research and decision visuals together. Run all preserved experiments through the canonical alpha_factory_v1/demos catalog, check prerequisites before launch, and follow the complete demo walkthrough. Business 3 adds an editable enterprise planner with exact portfolios, stress tests, a candidate-value comparison and portable evidence. Its redesigned research collection retains the original artwork, flowcharts and interactive replay. The release packages the original sample data and tests all 15 finite commands outside the source tree. Release notes. All original content, flowcharts and media remain.

Version 1.12.1 completes release delivery and evidence integrity.

Start here: verified installation, packaged operating guides, strict approved receipts and an Ascension Protocol Desk that works on both preserved routes. Release notes. All original diagrams and media remain.


Version 1.12.0 updates the complete Alpha-Factory package entry point.

Start with Alpha-Factory or the factory guide: packaged editable missions, cross-platform setup, exact FusionPlans and signed reviewed-work handoffs. All original diagrams and media remain. See release notes.


α-AGI Ascension — executable protocol

Version 1.11.0 connects the Ascension vision to a tested Solidity lifecycle. Open the Protocol Desk: cryptosealed ERC-721 Nova-Seeds, a validator risk oracle, MARK’s funding AMM, plan-restricted Sovereign treasuries and reputation-weighted job auctions with exact $AGIALPHA settlement and 1% payout burns. The native agent runs the delivered mission; local EVM receipts expose the entire sequence and capital recovery. Read the implementation and reproduction guide and release notes. This additive suite preserves all existing contracts, research and demos. Local execution is verified. The recorded mainnet deployment uses an earlier source profile; participant commissioning and review of the newer fixes remain outstanding.

$AGIALPHA Agent — release status

Version 1.10.1 strengthens signature verification, operator reliability and recovery. Legacy plugin signatures must verify even when listed in the registry. Inference has a total response deadline, expired workers cannot invalidate replacement work, and backup creation enforces its recovery limits. Use the current operator guide, release scope and release notes. The Decision Studio calculation policy remains 1.10.0, so existing replayable decisions retain their exact results.

Version 1.10.0 turns operational examples into reviewable staffing, delivery and decision plans. Open the Decision Studio for eleven editable operating cases: capital allocation, invention portfolios, supplier resilience, delivery scheduling, demand planning, service staffing, microgrid dispatch, proof debt, Nova-Seeds pilot review and second-order pipeline trials. Import your records, calculate constrained choices, and export a decision brief, row-level plan, proof backlog and replayable dossier. All 26 original catalog entries lead to a relevant workspace and retain their research implementation links. See methods, input contracts and a five-minute walkthrough.

Version 1.8.1 aligns the project with the latest 198-page AGI ALPHA manuscript. Read the manuscript and implementation map. Enter the Compounding Lab to learn and freeze a capability, test genuinely different future tasks, inspect four comparator arms, account for learning and review costs, and export the complete Evidence Docket. Positive transfer, regime failure and archive ablation are computed locally. Independent validation and broader manuscript promotion remain explicit proof obligations. Use the field guide or alpha-agent transfer-run --output run.json.

Version 1.7.0 adds Nova-Seeds Proof Bloom: five connected, evidence-gated experiences. Enter the foundry to turn a claim into native jobs, replay returned evidence, review exact artifacts, promote a scoped capability and reuse it in the next mission. Explore Nova-Seeds, Sovereign Bloom, the Alpha Business Ω-Lattice, Invention Automation and Proof Debt → AGI Jobs. The Proof Bloom field guide explains the proof protocol, native return path and recovery.

Version 1.6.0 adds the connected Insight Atlas and a refined GitHub Pages experience. Explore the Living Treasure Map, Second-Order Agency lab and Alpha under trial: exact scenario allocations, inspectable architecture comparisons, native research exports and replay-verified recovery. The Atlas field guide explains the calculations, evidence gates and limits. Patched cryptography, complete operator dependency auditing and stricter publication/CI controls are documented in the release readiness guide. Explore the new flagship missions and implementation map: Insight, encrypted Nova-Seeds, funding curves, Sovereign schedules, Council settlement and Architect policy search. The governance observatory makes the paper’s equations interactive and documents necessary mathematical corrections. Start with the operator guide, capability matrix and validation evidence. Install the official release wheel and hash-locked runtime, then run alpha-agent init and alpha-agent serve. For the current container demo profiles, use Docker Compose 2.20 or later; the older Compose minimum in the preserved historical documentation below no longer covers those profiles.

Start in the GitHub Pages workspace for checked research, allocation, scheduling and forecasting, real local text generation, reviewed exports and verification of signed agent results. The workspace guide explains privacy, offline use and the handoff to your agent. The complete demo catalog labels every launch path, sample replay, research backend and historical integration template.

The original vision, flywheels, examples and demos below are preserved; CI badges explicitly track main. Historical AGI/ASI, economic and compliance aspirations are not release guarantees. This is the $AGIALPHA project, separate from AGI Jobs. The previous state is preserved in baseline-2026-09-24.

Release Release acceptance

For repository administrators, current protection instructions use the actual check names Lint (ruff) and Smoke tests.

CI badges show live results and open their supporting checks. Health follows the latest watchdog workflow on main; Integration and Smoke read the current main commit's complete matrix results. Badge meanings and troubleshooting explain the scope of each check and where to find release evidence.

Smoke tests now run automatically across Linux, macOS and Windows on Python 3.11–3.13. Full browser builds include verified ONNX GPT-2 text generation that works offline after installation. GPT-2 is a small text-completion baseline, not an instruction-following assistant. The original PyTorch model assets remain available. Minimal browser builds retain the simulation; local chat reports missing model assets explicitly. Browser API credentials remain in memory.


See docs/DISCLAIMER_SNIPPET.md

This repository is a conceptual research prototype. References to "AGI" and "superintelligence" describe aspirational goals and do not indicate the presence of a real general intelligence. Use at your own risk. Nothing herein constitutes financial advice. MontrealAI and the maintainers accept no liability for losses incurred from using this software.

Ready to explore? Launch the α‑AGI Insight demo to see it in action.

Security Note

This project intentionally avoids reliance on Chainlink VRF or similar third-party subscription services. Randomness and related features are derived locally so the system remains self-contained and auditable.

Continuous Integration

PR CI 🚀 Integration CI — Insight Demo 🔥 Smoke Test 🩺 CI Health

The CI matrix is pinned to the canonical $AGIALPHA token contract (0xa61a3b3a130a9c20768eebf97e21515a6046a1fa, 18 decimals). Each workflow calls python scripts/check_agialpha_config.py to fail fast if the address, decimals, or workflow environment variables drift away from token.config.js or the Solidity constants. Run the same helper locally before dispatching CI to keep badges green and avoid PR surprises.

The canonical pull-request gate is ✅ PR CI. It runs Ruff plus the focused smoke test suite on pull requests, pushes to main, and merge queue runs.

The full 🚀 Integration CI — Insight Demo workflow is intentionally off the PR path. It runs on pushes to main, release tags (v* / release-*), and manual dispatch for maintainers. Push-to-main runs the full non-release validation matrix (actionlint, Ruff+Mypy matrix, pytest matrix, Insight Browser ESLint, Windows/macOS smoke, MkDocs, Docs Build, Docker build validation, and branch-protection guardrails). Tags/manual dispatch add release-only publish/deploy/signing stages.

🩺 CI Health hard-monitors the canonical required surface (✅ PR CI) and hard-monitors 🚀 Integration CI for merge-surface contexts. workflow_run watchdog executions remain rerun-only (no extra dispatch) because the upstream run already exists; scheduled/manual runs enforce both PR and merge surfaces with missing-run dispatch enabled. Self-monitoring remains opt-in (--include-self), and rerun support helps Repo-Healer progress beyond run-attempt-1 report-only triage. ADMIN_GITHUB_TOKEN enables branch-protection remediation while default tokens stay read-only for admin APIs.

Run CI locally

  1. Create and activate a Python 3.11–3.13 virtual environment, then upgrade pip:
    python3 -m venv .venv
    source .venv/bin/activate
    pip install -U pip
  2. Install required and optional Python dependencies (set ALPHA_FACTORY_FULL=1 for heavier extras or --wheelhouse <dir> when offline):
    python check_env.py --auto-install
  3. Run formatting and lint hooks:
    pre-commit run --all-files
  4. Execute the tests:
    pytest
  5. Trigger workflows from GitHub Actions when needed:
    • ✅ PR CI validates PR gate behavior.
    • 🚀 Integration CI — Insight Demo validates the full post-merge/release matrix.

Set branch protection required checks to:

  • ✅ PR CI / Lint (ruff)
  • ✅ PR CI / Smoke tests

Keep Require branches to be up to date enabled. Verify protections with:

python scripts/verify_branch_protection.py --apply --branch main

Track workflow health with:

python scripts/check_ci_status.py --wait-minutes 5 --stale-minutes 90 --pending-grace-minutes 45
# add --dispatch-failed only for explicit remediation runs

See docs/CI_ENFORCEMENT.md for the up-to-date enforcement checklist.

Quick Demo

Non-technical users can try the project with zero setup. Simply visit https://montrealai.github.io/AGI-Alpha-Agent-v0/alpha_agi_insight_v1/ in your browser. The README explains how this demo is built and deployed.

See Quick Deployment for build and deployment details. The 📚 Docs workflow is dispatched manually by the repository owner to publish the updated site to GitHub Pages.

Full documentation: https://montrealai.github.io/AGI-Alpha-Agent-v0/ (use the Docs link in the navigation bar)

The GitHub Pages site hosts the interactive demo under the alpha_agi_insight_v1/ directory. Click Docs in the navigation bar for the full manual.

View the interactive demo here: https://montrealai.github.io/AGI-Alpha-Agent-v0/alpha_agi_insight_v1/

Browse the visual demo gallery: https://montrealai.github.io/AGI-Alpha-Agent-v0/

Explore all demos: https://montrealai.github.io/AGI-Alpha-Agent-v0/alpha_factory_v1/demos/ – run ./scripts/open_subdir_gallery.py (or set AF_GALLERY_URL to your own mirror) for a local or online launch. Alternatively execute make subdir-gallery-open to build the gallery if needed and open it automatically. All browser demos include a mode toggle. Choose Offline to run a Pyodide simulation directly in your browser or switch to OpenAI API when you provide a key. The key is stored only in memory.

Smoke Test Workflow

Trigger the 🔥 Smoke Test job from the GitHub Actions tab to run linting, unit tests and a short 2‑year simulation in offline mode. The workflow verifies the ledger output and catches import errors or circular dependencies early.

Important: Run npm run fetch-assets before npm install or executing ./setup.sh to download the browser demo assets. Run this command in a fresh checkout—or delete existing wasm*/ files first—so placeholder files are replaced. After the download, verify checksums with python scripts/fetch_assets.py --verify-only. The helper retrieves the official Pyodide runtime from the jsDelivr CDN and the GPT‑2 small checkpoint directly from the Hugging Face CDN. The legacy wasm-gpt2.tar bundle is no longer used. Override HF_GPT2_BASE_URL to change the mirror, for example:

export HF_GPT2_BASE_URL="https://huggingface.co/openai-community/gpt2/resolve/main"

If npm run fetch-assets fails with a 401 or 404 error, download the GPT‑2 files manually:

python scripts/download_hf_gpt2.py models/gpt2

Each file can also be fetched individually using these official links:

curl -O https://huggingface.co/openai-community/gpt2/resolve/main/pytorch_model.bin
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/vocab.json
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/merges.txt
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/config.json

The model weights have SHA‑256 7c5d3f4b8b76583b422fcb9189ad6c89d5d97a094541ce8932dce3ecabde1421 for verification. See insight_browser_v1/index.md for additional details.

Launch \u03b1\u2011AGI Insight

Manual Deployment

The repository owner triggers the Docs workflow from the GitHub Actions tab. Simply click Run workflow to start the deployment. The job runs scripts/edge_human_knowledge_pages_sprint.sh to rebuild the Insight demo and MkDocs site, publishing the result to GitHub Pages. Once it finishes the live demo is available at https://montrealai.github.io/AGI-Alpha-Agent-v0/alpha_agi_insight_v1/.

Publish Demo Gallery

Ensure Python 3.11–3.13 (<3.14) and Node 22.17.1 are installed, then deploy the gallery and docs with a single command:

make gallery-deploy

make gallery-deploy wraps scripts/deploy_gallery_pages.sh, which calls scripts/generate_gallery_html.py to refresh docs/index.html and update the docs/gallery.html redirect.

See docs/GITHUB_PAGES_DEMO_TASKS.md for a detailed walkthrough. Once the build finishes, open the gallery locally with:

make gallery-open

Run make gallery-build to regenerate the site without deploying and open it in one step.

Open an individual demo directly:

make demo-open DEMO=alpha_agi_business_v1

Edge-of-Human-Knowledge Sprint

Run the wrapper to build and deploy the full GitHub Pages site with environment checks and offline validation. Use the shell or Python version:

./scripts/edge_human_knowledge_pages_sprint.sh
python scripts/edge_human_knowledge_pages_sprint.py

Ensure Python 3.11–3.13 (<3.14), Node 22.17.1 and mkdocs are installed. The script mirrors the Docs workflow used for manual deployment.

Browser Size Workflow

The 📦 Browser Size job ensures the Insight archive stays under 500 MiB (with a 750 MiB hard cap). Open Actions → 📦 Browser Size and click Run workflow to start the check. Repository owners can leave run_token blank. Others must provide the run_token that matches the DISPATCH_TOKEN secret. The workflow caches pip and npm dependencies using actions/setup-python and actions/setup-node. Node uses cache-dependency-path to reference alpha_factory_v1/demos/alpha_agi_insight_v1/insight_browser_v1/package-lock.json, alpha_factory_v1/core/interface/web_client/package-lock.json, alpha_factory_v1/core/interface/web_client/staking/package-lock.json and alpha_factory_v1/demos/alpha_agi_insight_v1/src/interface/web_client/package-lock.json so repeat runs skip redundant downloads and avoid the “Dependencies lock file is not found” warning. ci.yml stores these paths in the NODE_LOCKFILES environment variable so every setup-node step uses the same list. It applies the same paths for the tests, docs-build and Docker jobs. It preinstalls numpy, pandas, pytest and PyYAML so the environment check passes without network hiccups. During the run it also updates the browserslist cache inside alpha_factory_v1/demos/alpha_agi_insight_v1/insight_browser_v1 and alpha_factory_v1/core/interface/web_client using update-browserslist-db to ensure the generated assets target the latest browsers. When running offline or if the update fails, set BROWSERSLIST_IGNORE_OLD_DATA=true to continue without refreshing the cache. Update the version in .github/workflows/ci.yml and rerun npx update-browserslist-db --update-db --yes whenever dependencies change.

CI Workflow

The 🚀 Integration CI workflow verifies the Insight demo with linting, type checks, unit tests and a Docker build. Open Actions → 🚀 Integration CI — Insight Demo, select the branch or tag to test in the drop‑down and click Run workflow to dispatch the pipeline. This workflow also runs automatically on pushes to main and release tags (v*, release-*), while staying off pull requests. Push-to-main runs now execute the full non-release validation matrix, while release tags/manual dispatch append publish/deploy tasks. Each job begins by verifying the actor matches the repository owner only for manual dispatches; push and tag runs execute automatically for normal integration validation. Because the first job checks ${{ github.actor }} against ${{ github.repository_owner }}, you must own the repository to run the workflow from manual dispatch. Jobs following the main test stage include if: always() so the Windows and macOS smoke tests, documentation build and Docker jobs execute even when the lint or unit tests fail. This behavior helps confirm that cross‑platform builds and docs generation succeed while debugging failures. Dependency hashes are fully locked, including setuptools, so pip install -r requirements.lock succeeds across Python versions. The Windows smoke job now builds the Insight browser before running tests, ensuring the service worker is present for the cache version check. Browser assets are cached across jobs using a deterministic hash derived from the expected checksums, so later stages reuse the same files. The docs and Docker jobs automatically fetch any missing assets and open a pull request when checksums drift. See CI_WORKFLOW.md for a detailed job overview. All Node.js steps pin the same lockfiles via cache-dependency-path so actions/setup-node caches npm packages correctly and avoids "Dependencies lock file is not found" warnings. The paths are:

alpha_factory_v1/demos/alpha_agi_insight_v1/insight_browser_v1/package-lock.json
alpha_factory_v1/core/interface/web_client/package-lock.json
alpha_factory_v1/core/interface/web_client/staking/package-lock.json
alpha_factory_v1/demos/alpha_agi_insight_v1/src/interface/web_client/package-lock.json

To publish a release, create a Git tag and run the same workflow on that tag. The Docker job pushes the agi-insight-demo image to GitHub Container Registry while the deploy stage attaches the built web client archive to a GitHub release. If any later step fails the workflow automatically restores the previous latest tag to avoid shipping a broken image.

Build & Test Workflow

The 🐳 Build & Test job runs linting, tests and container builds. Open Actions → 🐳 Build & Test and click Run workflow to start the pipeline. Only the repository owner can run this workflow. Each job verifies the actor first and exits immediately for non‑owners, keeping the rest of the jobs from being skipped. See ADMIN_ACTIONS.md for details on the manual workflow restrictions and protected environments.

Docker image tags must use all lowercase characters. The workflow's "Prepare lowercase image name" step sets REPO_OWNER_LC to the lowercased repository owner so tags like ghcr.io/montrealai are valid.

CI Quick Start

To replicate the CI pipeline locally:

python scripts/check_python_deps.py
python check_env.py --auto-install
pytest --cov --cov-report=xml
pre-commit run --all-files

Launch the integration workflow manually via Actions → 🚀 Integration CI — Insight Demo and click Run workflow as described in AGENTS.md. The workflow performs linting, type checks, the full unit test matrix on Python 3.11 and 3.12, Windows and macOS smoke tests, documentation builds, Docker builds and an optional deploy step for tagged releases.

Verify Docker image signature

The release workflow signs the container using cosign. Validate the signature before deploying a new version:

cosign verify ghcr.io/montrealai/agi-insight-demo:latest

Successful verification proves the image came from this repository's CI.

Quickstart

./quickstart.sh
# or using Docker
docker compose up --build
# or one-click image
./run_quickstart.sh

Run npm run fetch-assets before npm install or executing ./setup.sh to download the Insight demo assets. Delete any old wasm*/ directories or start from a clean checkout so placeholders are replaced. After fetching, verify the files with python scripts/fetch_assets.py --verify-only. The helper retrieves the official Pyodide runtime from the jsDelivr CDN and the GPT‑2 small checkpoint from Hugging Face. Override HF_GPT2_BASE_URL or PYODIDE_BASE_URL to use alternate mirrors. See insight_browser_v1/index.md for a detailed guide. You can also run python scripts/download_gpt2_small.py to retrieve the model directly:

python scripts/download_gpt2_small.py models/
# downloads https://huggingface.co/openai-community/gpt2/resolve/main/pytorch_model.bin ...

As a last resort use python scripts/download_openai_gpt2.py 124M.

Requires Python 3.11–3.13 (<3.14) and Docker Compose ≥2.5.

Alternatively, run the pre-built image directly:

docker run --pull=always -p 8000:8000 ghcr.io/montrealai/alpha-factory:latest

The workflow publishes a separate image for each Python version with tags py311, py312 and py313. Only the Python 3.13 build also updates the latest tag so ghcr.io/montrealai/alpha-factory:latest always refers to the most recent Python 3.13 image.

Note The Dockerfiles in this repository pin the base image to Python 3.13. Keep this in sync with the highest Python version listed in the CI matrix when updating workflows.

Replace latest with a commit SHA to run that exact build:

docker run --pull=always -p 8000:8000 ghcr.io/montrealai/alpha-factory:<commit>

Set OPENAI_API_KEY and other required secrets in your environment or .env before launching the container. The orchestrator prints the project disclaimer when it starts.

Supported OS: Ubuntu 22.04+, Debian 12+, macOS 12+ and Windows 11 via WSL 2 (recommended for Windows users). Native Windows paths frequently break volume mounts. Clone this repository inside the WSL file system to avoid these issues.

wsl --install
wsl --set-default-version 2
wsl --update
# enable "Use the WSL 2 based engine" in Docker Desktop

Clone the repository inside your WSL home directory to avoid path translation errors.

See docs/INTRO_BASICS.md for the bare essentials or docs/QUICKSTART_BASICS.md for a minimal walkthrough.

Watch the run here: Quickstart video · Asciinema link

See the documentation for detailed steps and an overview of the project. For a concise high-level picture of how the main pieces fit together, see docs/ARCHITECTURE.md.

META-AGENTIC α‑AGI 👁️✨

v0.1.0‑alpha

Official and pioneering definition – Meta-Agentic (adj.): Describes an agent whose primary role is to create, select, evaluate, or re‑configure other agents and the rules governing their interactions, thereby exercising second‑order agency over a population of first‑order agents. The term was pioneered by Vincent Boucher, President of MONTREAL.AI.

flowchart TD
    Insight["🎖️ α‑AGI Insight 👁️✨"]
    Seeds["🌱💫 α-AGI Nova-Seeds 🔐"]
    Mark["α-AGI MARK 🔮🌌✨"]
    Sovereign["🎖️ α‑AGI Sovereign 👑✨"]
    Biz["🌸 α‑AGI Business 👁️✨"]
    Market["🪐 Marketplace 👁️✨"]
    Jobs["📜 α‑AGI Jobs 👁️✨"]
    Agents["👾👾👾🌌👾👾👾 α‑AGI Agents 👁️✨"]
    Reservoir["💎 α‑AGI Value Reservoir"]
    Architect["🎖️ α‑AGI Architect 🔱✨"]
    Council["🔐 α‑AGI Council 👁️✨"]
    Nodes["🖥️ α‑AGI Nodes 👁️✨"]

    Insight --> Seeds --> Mark --> Sovereign
    Sovereign --> Biz --> Market
    Market -->|spawn| Jobs --> Agents
    Agents -- success --> Reservoir
    Jobs -- ΔΣUSD --> Reservoir
    Reservoir -. reinvest .-> Seeds
    Reservoir -. fund .-> Market
    Agents <---> Nodes
    Architect <--> Sovereign
    Architect <--> Insight
    Council --> Sovereign
Loading

Humanity’s Structured Rise to Economic Supremacy via Strategic AGI Mastery

🎖️ α‑AGI Insight 👁️✨ — Beyond Human Foresight

Where human foresight reaches its limits, α‑AGI Insight sees beyond. Humanity stands at the precipice of history’s most profound economic transformation. α‑AGI Insight identifies with pinpoint accuracy those sectors poised for imminent disruption by Artificial General Intelligence (AGI). With authoritative and rigorously validated projections estimating economic opportunities surpassing $15 Quadrillion (15 000 trillion USD), today’s strategic anticipation unlocks extraordinary economic advantages tomorrow.

  • Precision Forecasting — Identify and proactively engage critical sectors before AGI disruption.
  • First‑Mover Advantage — Maximize returns through strategic foresight and superior positioning. A static demo is available via GitHub Pages. See Quick Deployment for guidance on building the docs and publishing your own copy.

🎖️ α‑AGI Sovereign 👁️✨ — Autonomous Economic Transformation

Meta‑Agentic mastery at global scale. α‑AGI Sovereign represents a revolutionary class of autonomous, blockchain‑based enterprises deploying advanced Meta‑Agentic frameworks. Through dynamically evolving swarms of intelligent agents, these enterprises systematically identify and transform global inefficiencies into measurable economic value (“$AGIALPHA”), fundamentally reshaping market dynamics and strategically realigning global economic structures.

  • α‑AGI Marketplace 👁️✨ — Decentralized global platform matching strategic AGI tasks with optimal execution.
    • α‑AGI Jobs 👁️✨ — Autonomous missions precisely targeting identified inefficiencies.
    • α‑AGI Agents 👁️✨ — Adaptive, self‑optimizing intelligent agents executing α‑Jobs, yielding immediate economic returns.

Strategic Edge:

  • Decentralized autonomy ensures superior agility and resilience.
  • Strategically validated methodologies guarantee consistent economic leadership.

Quick Start

Local: ./quickstart.sh   |   Docker: docker compose up --build

An interactive Colab notebook demonstrates the same zero‑data Insight search loop. Open colab_alpha_agi_insight_v1.ipynb in Google Colab to try it online.

Clone the repository at the v0.1.0-alpha tag and run the helper script to start the Insight demo locally:

git clone --branch v0.1.0-alpha https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git
cd AGI-Alpha-Agent-v0
python -c "import alpha_factory_v1; print(alpha_factory_v1.__version__)"  # prints 0.1.0-alpha
python check_env.py --auto-install  # may run for several minutes
# NumPy and pandas are required for realistic results; omit or add
# `--allow-basic-fallback` to bypass this check.
# Abort with Ctrl+C and rerun with '--timeout 300' to fail fast
./quickstart.sh
Run `pre-commit run --all-files` after the dependencies finish installing.

Offline example using a local wheelhouse:

WHEELHOUSE=$(pwd)/wheels AUTO_INSTALL_MISSING=1 ./quickstart.sh

If the default mirrors are blocked, set PYODIDE_BASE_URL or HF_GPT2_BASE_URL before running npm run fetch-assets:

export PYODIDE_BASE_URL="https://cdn.jsdelivr.net/pyodide/v0.28.0/full"
export HF_GPT2_BASE_URL="https://huggingface.co/openai-community/gpt2/resolve/main"
npm run fetch-assets

Or launch the full stack with Docker:

docker compose up --build

Minimal Install

The default requirements.txt pulls in a lean set of packages for the offline demos and tests:

pip install -r requirements.txt

Full Feature Install

Install the heavier extras for finance, graph back‑ends and large language models:

pip install -r alpha_factory_v1/requirements.txt
# or set ALPHA_FACTORY_FULL=1 when running `check_env.py --auto-install`

Detailed step‑by‑step instructions, including Colab usage, are available in the documentation.

For advanced options, see the 5‑Minute Quick‑Start and Docker Quickstart sections below.

Running the Insight Demo

For the browser-based version, see insight_browser_v1/index.md. It requires Node.js ≥22.17. Install the dependencies with npm ci and build the static assets with npm run build before launching. The repository includes a .nvmrc file so you can simply run nvm use to select the correct Node version.

The α‑AGI Insight demo ships with an offline‑friendly command line interface. After installation, launch the official demo via:

alpha-agi-insight-v1 --episodes 5
# Or run directly from the package
python -m alpha_factory_v1.demos.alpha_agi_insight_v1 --episodes 5

When API keys are configured the program automatically uses the OpenAI Agents runtime. Otherwise it falls back to the local Meta‑Agentic Tree Search. The orchestrator also cleans up the OpenAI runtime on exit to release resources.

For production use, invoke the official demo which automatically checks the environment, selects the best runtime and optionally starts the Google ADK gateway:

alpha-agi-insight-v1 --episodes 5

This wrapper transparently falls back to the offline Meta‑Agentic Tree Search when API credentials are absent, ensuring the demo runs anywhere.

For a guaranteed offline run without external dependencies, use:

AGI_INSIGHT_OFFLINE=1 alpha-agi-insight-v1 --episodes 5

Setting AGI_INSIGHT_OFFLINE=1 ensures the search loop never attempts network access.

When the host cannot reach the internet the environment checker prints a warning and the demos continue in offline mode using any cached data. Optional downloads are skipped automatically.

Several demos ship with small CSV snapshots for offline mode. These samples mirror data from the demo-assets repository and cover roughly March–April 2024.

Meta-Agentic Tree Search Demo

An offline-friendly reference implementation focused on recursive agent-to-agent rewrites lives in meta_agentic_tree_search_v0/README.md. It demonstrates the best‑first search behind the other examples and runs without external APIs.

Offline Mode

Follow these steps when working without internet access. See the documentation for a summary of required environment variables.

  1. Build a wheelhouse on a machine with connectivity:

    ./scripts/build_offline_wheels.sh

    The script collects all required wheels under wheels/. Copy this directory to the offline host, for example using scp or a USB drive:

    scp -r wheels user@offline-host:/path/to/AGI-Alpha-Agent-v0/

    Then set the environment variable on the target machine:

    export WHEELHOUSE="/path/to/AGI-Alpha-Agent-v0/wheels"
  2. Install from the wheelhouse and verify packages. The setup script automatically uses a wheels/ directory in the repository root when WHEELHOUSE is unset:

    AUTO_INSTALL_MISSING=1 ./codex/setup.sh
    python check_env.py --auto-install --wheelhouse "$WHEELHOUSE"
    pip check

When network access is unavailable, install packages directly from the wheelhouse:

pip install --no-index --find-links "$WHEELHOUSE" -r requirements.txt
# Install demo extras offline
pip install --no-index --find-links "$WHEELHOUSE" -r \
  alpha_factory_v1/demos/era_of_experience/requirements.lock

check_env.py uses the wheels under $WHEELHOUSE. Set WHEELHOUSE="$WHEELHOUSE" when running pre-commit or the tests so dependencies install from the local cache. See Offline Setup for more details. A short reference lives in the documentation. If package installation hangs for more than ten minutes, check_env.py will time out and suggest using --wheelhouse for offline installs.

Run the environment check again when the machine is completely air‑gapped:

python check_env.py --auto-install --wheelhouse "$WHEELHOUSE"

This mirrors the instructions in alpha_factory_v1/scripts/README.md.

See the documentation for a concise summary of the wheelhouse setup.

  1. Download a .gguf weight and set LLAMA_MODEL_PATH:

    mkdir -p ~/.cache/llama
    curl -L -o ~/.cache/llama/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf \
      https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf
    export LLAMA_MODEL_PATH=~/.cache/llama/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf

    Common weights and typical CPU throughput:

    Model Size ~tokens/s
    TinyLlama‑1.1B‑Chat Q4_K_M 380 MB ~20
    Llama‑3‑8B‑Instruct Q4_K_M 4 GB ~5
    Mixtral‑8×7B‑Instruct Q4_0 7 GB ~3

    Install llama-cpp-python or ctransformers to enable offline inference.

  2. Fetch and build the browser assets (requires Node.js) to run the Insight demo fully offline:

    cd alpha_factory_v1/demos/alpha_agi_insight_v1/insight_browser_v1
    npm run fetch-assets
    npm ci
    npm run build

    Skipping this step or running without Node.js prevents the service worker from being generated, so offline functionality is limited.

  3. Bundle Pyodide for offline demos

    make gallery-build

    This command generates the site/ directory with the Pyodide runtime and demo assets so the browser examples work without a network connection. The service worker caches these files. Use a hard refresh (Ctrl+Shift+R) or clear site data to pick up new releases.

  4. Skip browser downloads when running the web demo tests offline:

    PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1 npm test
  5. Enable offline inference by setting AGI_INSIGHT_OFFLINE=1 in .env or the environment (ensure llama-cpp-python or ctransformers is installed).

  6. Disable broadcasting to avoid network calls:

    export AGI_INSIGHT_BROADCAST=0
  7. Seed the lineage database from existing DGM logs using --import-dgm.

    python -m alpha_factory_v1.demos.alpha_agi_insight_v1.src.interface.cli \
      simulate --import-dgm path/to/dgm/logs

    Sample sector definitions live in

    alpha_factory_v1/demos/alpha_agi_insight_v1/docs/sectors.sample.json. Pass this file with --sectors-file to forecast specific industries.

    The built-in Sector-Shock-10 dataset ships with the package and is located using importlib.resources when running the demo. This allows simulate to score forecasts even when the repository layout is not available.

Example (using --sectors-file to customise the simulation):

AGI_INSIGHT_OFFLINE=1 AGI_INSIGHT_BROADCAST=0 \
python -m alpha_factory_v1.demos.alpha_agi_insight_v1.src.interface.cli simulate \
  --curve linear --k 8 --x0 0.0 --llama-model-path "$LLAMA_MODEL_PATH" \
  --offline --energy 2.0 --entropy 0.5 \
  --mut-rate 0.1 --xover-rate 0.5 \
  --sectors-file alpha_factory_v1/demos/alpha_agi_insight_v1/docs/sectors.sample.json

Produces output similar to:

OPENAI_API_KEY missing – offline mode enabled
year | capability | affected
-----+------------+---------
1    | 0.88       |
2    | 0.98       |
3    | 1.00       |
4    | 1.00       |
5    | 1.00       |

🎖️ α‑AGI Architect 👁️✨ — Foundational Operational Blueprint

Empowering Meta‑Agentic visionaries with strategic infrastructure. At the core of α‑AGI Ascension is α‑AGI Architect — the foundational operational framework for scalable global deployment. Rooted in the groundbreaking “Multi‑Agent AI DAO” model, α‑AGI Architect delivers immediate, scalable, and adaptive infrastructure ensuring continuous strategic evolution.

  • Robust feedback loops driving continuous refinement between Sovereign operations and Architect infrastructure.
  • Engineered for rapid global scalability and strategic responsiveness.
flowchart TD
    %% ───────────────────────────  CORE LAYERS  ───────────────────────────
    A[🚀 🎖️ α-AGI Ascension 🌌]
    B[🎖️ α-AGI Insight 👁️✨]
    C[🎖️ α-AGI Sovereign 👁️✨]
    D[🎖️ α-AGI Marketplace 👁️✨]
    E[🎖️ α-AGI Jobs 👁️✨]
    F[🎖️ α-AGI Agents 👁️✨]
    G[🎖️ α-AGI Architect 👁️✨]
    V[💎 Infinite Value Reservoir]

    %% ───────────────────────────  PRIMARY FLOWS  ─────────────────────────
    A --> B
    B --> C
    C --> D
    D --> E
    D --> F
    C --> G
    G -.↺ Continuous optimisation .-> C

    %% ───────────────────────  WEALTH FEEDBACK LOOPS  ─────────────────────
    E -- Harvest ΔΣUSD --> V
    F -- Compound returns --> V
    V -- Reinvest capital --> D

    %% ──────────────────────────────  STYLE  ──────────────────────────────
    classDef asc     fill:#0f172a,color:#ffffff,font-weight:bold,stroke-width:0px
    classDef insight fill:#1e3a8a,color:#ffffff,stroke-width:0px
    classDef market  fill:#0e7490,color:#ffffff,stroke-width:0px
    classDef value   fill:#fde047,color:#000000,font-weight:bold,stroke-width:0px

    class A asc
    class B insight
    class C,G insight
    class D,E,F market
    class V value

    linkStyle default stroke-width:2px
Loading


Deploy Now

Open‑source framework for immediate strategic action: github.com/MontrealAI/AGI-Alpha- Agent-v0


🔱✨ Conclusion

[ 🎖️ α‑AGI Ascension 🌌 ] launches humanity into an entirely new economic epoch. By systematically harnessing AGI’s transformative capabilities, it rewrites global economic structures, implicitly realigning international power dynamics and propelling humanity toward unprecedented sovereign economic prosperity.




Mission 🎯  Identify 🔍 → Learn 📚 → Think 🧠 → Design 🎨 → Strategise ♟️ → Execute ⚡ — compounding real‑world α across all industries.

Global markets seep USD ✧ trillions/yr in latent opportunity — “alpha” in the broadest sense:
pricing dislocations • supply‑chain entropy • novel drug targets • policy loopholes • undiscovered materials.

Alpha‑Factory v1 is an antifragile constellation of self‑improving Agentic α‑AGI Agents 👁️✨ orchestrated to spot live alpha across any industry and transmute it into compounding value.

Definition: An α‑AGI Business 👁️✨ is an on‑chain autonomous enterprise (.alpha.agi.eth) that unleashes a swarm of self‑improving agentic α‑AGI agents 👁️✨ (.alpha.agent.agi.eth) to hunt down inefficiencies across any domain and transmute them into $AGIALPHA.

Built atop OpenAI Agents SDK, Google ADK, A2A protocol, and Anthropic’s Model Context Protocol, the stack runs cloud‑native or air‑gapped, hot‑swapping between frontier LLMs and distilled local models.

TL;DR Quick Start

Check out the v0.1.0-alpha tag for a reproducible environment.

git clone --branch v0.1.0-alpha https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git
cd AGI-Alpha-Agent-v0
python3 -m venv .venv
source .venv/bin/activate
# Install runtime dependencies
# Install runtime dependencies
pip install -r requirements.lock  # pinned versions for deterministic setup
# Optional ADK/MCP integration
pip install google-adk mcp
# Requires Python 3.11–3.13 (<3.14)
./quickstart.sh
Run `pre-commit run --all-files` after the dependencies finish installing.
# Open http://localhost:8000/docs in your browser

The adapters initialise automatically when these optional packages are present.

Optional Packages

Install these extras to unlock additional features:

  • pip install gradio – enables the MuZero planning dashboard.
  • pip install openai-agents==0.0.17 – activates the official Agents runtime used for commentary.
  • pip install google-adk and set ALPHA_FACTORY_ENABLE_ADK=true – starts the Google ADK gateway for cross‑organisation agent exchange.
  • Install domain‑specific extras as needed (e.g. httpx, feedparser, networkx, lightgbm, kafka-python, tldextract). Each agent logs a warning when a library is missing and continues in degraded mode.

Offline installations can omit these lines from the relevant requirements.txt files if the Agents SDK or ADK gateway are not needed.

To regenerate requirements.lock from requirements.txt with hashes, run:

pip-compile --generate-hashes --output-file requirements.lock requirements.txt

Once the API server is running you can launch a simulation:

curl -X POST http://localhost:8000/simulate \
  -H "Authorization: Bearer $API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"horizon": 5, "pop_size": 6, "generations": 3, "mut_rate": 0.1, "xover_rate": 0.5, "curve": "linear", "energy": 1.0, "entropy": 1.0}'

Further Reading


Contributing

See AGENTS.md for the full contributor guide.

Pre‑commit Hooks

After running ./codex/setup.sh, which ensures pre-commit==4.2.0 is installed, install the hooks and run a full check:

# Install the exact version if the setup script didn't already
pip install pre-commit==4.2.0
pre-commit install
pre-commit run --all-files   # verify hooks after setup
pre-commit run --files <paths>   # before each commit

Run pre-commit run --all-files once after the setup script to confirm everything is formatted correctly. These commands mirror the steps in AGENTS.md and keep commits consistent. After editing .github/workflows/ci.yml, run:

pre-commit run --files .github/workflows/ci.yml
python tools/update_actions.py

to validate the workflow with actionlint before committing. Before opening a pull request, run pre-commit run --all-files to ensure all hooks succeed. Run python check_env.py --auto-install before invoking these commands so optional hook dependencies are installed. When working offline, pass --wheelhouse <dir> or set WHEELHOUSE to install from a local cache. If pre-commit isn't found or the version differs, install it with pip install pre-commit==4.2.0.

When editing the web UI, preserve existing ARIA labels so the interface remains accessible.

Development Setup

Install the Python dependencies with the helper script:

scripts/setup_env.sh

The script checks for Python 3.11–3.13 (<3.14) and installs requirements.txt and requirements-dev.txt.

When preparing an offline environment, build a wheelhouse on a machine with internet access:

./scripts/build_offline_wheels.sh

Copy the resulting wheels/ directory to the target host and set WHEELHOUSE=$(pwd)/wheels before running check_env.py or the tests so packages install from the local cache. The repository does not ship these prebuilt wheels.

📜 Table of Contents

  1. Design Philosophy
  2. System Topology 🗺️
  3. World‑Model & Planner 🌌
  4. Agent Gallery 🖼️ (12 agents)
  5. Demo Showcase 🎬 (14 demos)
  6. Memory & Knowledge Fabric 🧠
  7. 5‑Minute Quick‑Start 🚀 6.1. Running Tests 🧪 6.2. Marketplace Demo Example 🛒 6.3. Offline Mode
    • Set LLAMA_MODEL_PATH to the downloaded .gguf weight
    • AGI_INSIGHT_BROADCAST=0 disables blockchain broadcasting
    • Example:
      AGI_INSIGHT_OFFLINE=1 AGI_INSIGHT_BROADCAST=0
        python -m alpha_factory_v1.demos.alpha_agi_insight_v1.src.interface.cli
        simulate --offline --energy 2.0 --entropy 0.5 \
        --mut-rate 0.1 --xover-rate 0.5 \
        --llama-model-path "$LLAMA_MODEL_PATH"
  8. Deployment Recipes 🍳 7.1. Deploying securely 🚀
  9. Governance & Compliance ⚖️
  10. Observability 🔭
  11. Safety & Security 🛡️
  12. Extending the Mesh 🔌
  13. Troubleshooting 🛠️
  14. Roadmap 🛣️
  15. Credits 🌟
  16. License 📝

0 · Design Philosophy

“We have shifted from big‑data hoarding to big‑experience compounding.” — Era of Experience.

  • Experience‑First Loop — Sense → Imagine (MuZero‑style latent planning) → Act → Adapt.
  • AI‑GA Autogenesis — The factory meta‑evolves new agents and curricula inspired by Clune’s AI‑Generating Algorithms.
  • Graceful Degradation — GPU‑less? No cloud key? Agents fall back to distilled local models & heuristics.
  • Zero‑Trust Core — SPIFFE identities, signed artefacts, guard‑rails, exhaustive audit logs.
  • Polyglot Value — Everything is normalised to a common alpha Δ∑USD lens.

1 · System Topology 🗺️

flowchart LR
  ORC([🛠️ Orchestrator])
  WM[(🌌 World‑Model)]
  MEM[(🔗 Vector‑Graph Memory)]
  subgraph Agents
    FIN(💰)
    BIO(🧬)
    MFG(⚙️)
    POL(📜)
    ENE(🔋)
    SUP(📦)
    RET(🛍️)
    CYB(🛡️)
    CLM(🌎)
    DRG(💊)
    SCT(⛓️)
    TAL(🧑‍💻)
  end
  ORC -- A2A --> Agents
  Agents -- experience --> WM
  WM -- embeddings --> MEM
  ORC -- Kafka --> DL[(🗄️ Data Lake)]
Loading
  • Orchestrator auto‑discovers agents (see backend/agents/__init__.py) and exposes a unified REST + gRPC facade.
  • World‑Model uses MuZero‑style latent dynamics for counterfactual planning.
  • Memory Fabric = pgvector + Neo4j for dense & causal recall.

2 · World‑Model & Planner 🌌

Component Source Tech Role
Latent Dynamics MuZero++ Predict env transitions & value
Self‑Play Curriculum POET‑XL Generates alpha‑labyrinth tasks
Meta‑Gradient AI‑GA Evolves optimiser hyper‑nets
Task Selector Multi‑Armed Bandit Schedules agent ↔ world‑model interactions

3 · Agent Gallery 🖼️

flowchart TD
    ORC["🛠️ Orchestrator"]
    GEN{{"🧪 Env‑Generator"}}
    LRN["🧠 MuZero++"]

    subgraph Agents
        FIN["💰"]
        BIO["🧬"]
        MFG["⚙️"]
        POL["📜"]
        ENE["🔋"]
        SUP["📦"]
        RET["🛍️"]
        MKT["📈"]
        CYB["🛡️"]
        CLM["🌎"]
        DRG["💊"]
        SMT["⛓️"]
    end

    %% message flows
    GEN -- tasks --> LRN
    LRN -- policies --> Agents
    Agents -- skills --> LRN

    ORC -- A2A --> FIN
    ORC -- A2A --> BIO
    ORC -- A2A --> MFG
    ORC -- A2A --> POL
    ORC -- A2A --> ENE
    ORC -- A2A --> SUP
    ORC -- A2A --> RET
    ORC -- A2A --> MKT
    ORC -- A2A --> CYB
    ORC -- A2A --> CLM
    ORC -- A2A --> DRG
    ORC -- A2A --> SMT
    ORC -- A2A --> GEN
    ORC -- A2A --> LRN

    ORC -- Kafka --> DATALAKE["🗄️ Data Lake"]
    FIN -.->|Prometheus| GRAFANA{{"📊"}}
Loading
# Agent Path Prime Directive Status Key Env Vars
1 Finance 💰 finance_agent.py Multi‑factor alpha & RL execution Prod BROKER_DSN
2 Biotech 🧬 biotech_agent.py CRISPR & assay proposals Prod OPENAI_API_KEY
3 Manufacturing ⚙️ manufacturing_agent.py CP‑SAT optimiser Prod SCHED_HORIZON
4 Policy 📜 policy_agent.py Statute QA & diffs Prod STATUTE_CORPUS_DIR
5 Energy 🔋 energy_agent.py Spot‑vs‑forward arbitrage Beta ISO_TOKEN
6 Supply‑Chain 📦 supply_chain_agent.py Stochastic MILP routing Beta SC_DB_DSN
7 Retail Demand 🛍️ retail_demand_agent.py SKU forecast & pricing Beta POS_DB_DSN
8 Cyber‑Sec 🛡️ cyber_threat_agent.py Predict & patch CVEs Beta VT_API_KEY
9 Climate Risk 🌎 climate_risk_agent.py ESG stress tests Beta NOAA_TOKEN
10 Drug‑Design 💊 drug_design_agent.py Diffusion + docking Incub CHEMBL_KEY
11 Smart‑Contract ⛓️ smart_contract_agent.py Formal verification Incub ETH_RPC_URL
12 Talent‑Match 🧑‍💻 talent_match_agent.py Auto‑bounty hiring Incub —
%% Legend
%%  solid arrows  = primary value‑flow
%%  dashed arrows = secondary / supporting influence
%%  node emojis   = domain archetypes

graph TD
    %% Core pillars
    FIN["💰 Finance"]
    BIO["🧬 Biotech"]
    MFG["⚙️ Manufacturing"]
    POL["📜 Policy / Reg‑Tech"]
    ENE["🔋 Energy"]
    SUP["📦 Supply‑Chain"]
    RET["🛍️ Retail / Demand"]
    CYB["🛡️ Cyber‑Security"]
    CLM["🌎 Climate"]
    DRG["💊 Drug Design"]
    SMT["⛓️ Smart Contracts"]
    TLT["🧑‍💼 Talent"]

    %% Derived transversal competences
    QNT["📊 Quant R&D"]
    RES["🔬 Research Ops"]
    DSG["🎨 Design"]
    OPS["🔧 DevOps"]

    %% Primary value‑creation arcs
    FIN -->|Price discovery| QNT
    FIN -->|Risk stress‑test| CLM
    BIO --> DRG
    BIO --> RES
    MFG --> SUP
    ENE --> CLM
    RET --> FIN
    POL --> CYB
    SMT --> FIN

    %% Cross‑pollination (secondary, dashed)
    FIN -.-> POL
    SUP -.-> CLM
    CYB -.-> OPS
    DRG -.-> POL
    QNT -.-> RES
    RET -.-> DSG

    %% Visual grouping
    subgraph Core
        FIN
        BIO
        MFG
        POL
        ENE
        SUP
        RET
        CYB
        CLM
        DRG
        SMT
        TLT
    end
    classDef core fill:#0d9488,color:#ffffff,stroke-width:0px;
Loading

Each agent exports a signed proof‑of‑alpha message to the Kafka bus, enabling cross‑breeding of opportunities.

sequenceDiagram
    participant User
    participant ORC as Orchestrator
    participant FIN as 💰
    participant GEN as 🧪
    User->>ORC: /alpha/run
    ORC->>GEN: new_world()
    GEN-->>ORC: env_json
    ORC->>FIN: act(env)
    FIN-->>ORC: proof(ΔG)
    ORC-->>User: artefact + KPI
Loading

4 · Demo Showcase 🎬

# Folder Emoji Lightning Pitch Alpha Contribution Start Locally
1 aiga_meta_evolution 🧬 Agents evolve new agents; genetic tests auto‑score fitness. Expands strategy space, surfacing fringe alpha. cd alpha_factory_v1/demos/aiga_meta_evolution && ./run_aiga_demo.sh
2 alpha_agi_business_v1 🏦 Auto‑incorporates a digital‑first company end‑to‑end. Shows AGI turning ideas → registered business. ./alpha_factory_v1/demos/alpha_agi_business_v1/run_business_v1_demo.sh [--pull] [--gpu] (docs: http://localhost:8000/docs)
3 alpha_agi_business_2_v1 🏗 Iterates business model with live market data RAG. Continuous adaptation → durable competitive alpha. ./alpha_factory_v1/demos/alpha_agi_business_2_v1/run_business_2_demo.sh
4 alpha_agi_business_3_v1 📊 Financial forecasting & fundraising agent swarm. Optimises capital stack for ROI alpha. ./alpha_factory_v1/demos/alpha_agi_business_3_v1/run_business_3_demo.sh
5 alpha_agi_marketplace_v1 🛒 Peer‑to‑peer agent marketplace simulating price discovery. Validates micro‑alpha extraction via agent barter. docker compose -f demos/docker-compose.marketplace.yml up
6 alpha_asi_world_model 🌌 Scales MuZero‑style world‑model to an open‑ended grid‑world. Stress‑tests anticipatory planning for ASI scenarios. docker compose -f demos/docker-compose.asi_world.yml up
7 cross_industry_alpha_factory 🌐 Full pipeline: ingest → plan → act across 4 verticals. Proof that one orchestrator handles multi‑domain alpha. ./alpha_factory_v1/demos/cross_industry_alpha_factory/deploy_alpha_factory_cross_industry_demo.sh
8 era_of_experience 🏛 Lifelong RL stack blending real & synthetic experience streams. Showcases sensor-motor tools, grounded rewards & non-human reasoning. cd alpha_factory_v1/demos/era_of_experience && ./run_experience_demo.sh
9 finance_alpha 💹 Live momentum + risk‑parity bot on Binance test‑net. Generates real P&L; stress‑tested against CVaR. ./alpha_factory_v1/demos/finance_alpha/deploy_alpha_factory_demo.sh
10 macro_sentinel 🌐 GPT‑RAG news scanner auto‑hedges with CTA futures. Shields portfolios from macro shocks. docker compose -f demos/docker-compose.macro.yml up
11 muzero_planning ♟ MuZero in 60 s; online world‑model with MCTS. Distills planning research into a one‑command demo. ./alpha_factory_v1/demos/muzero_planning/run_muzero_demo.sh
12 self_healing_repo 🩹 CI fails → agent crafts patch ⇒ PR green again. Maintains pipeline uptime alpha. docker compose -f demos/docker-compose.selfheal.yml up
13 meta_agentic_tree_search_v0 🌳 Recursive agent rewrites via best‑first search. Rapidly surfaces AGI-driven trading alpha. mats-bridge --episodes 3
14 alpha_agi_insight_v1 👁️ Zero‑data search ranking AGI‑disrupted sectors. Forecasts sectors primed for AGI transformation. alpha-agi-insight-v1 --episodes 5

Colab? Each folder ships an *.ipynb that mirrors the Docker flow with free GPUs.

The official Docker image bundles PyTorch 2.2.x and Ray 2.10.0. The notebooks install PyTorch from the PyTorch wheel index and pin Ray to the same version for compatibility.

  • Solving AGI Governance — Monte‑Carlo governance simulation with optional OpenAI‑Agents/ADK integration. Colab
  • Self‑Healing Repo — agents automatically craft patches when CI fails. The underlying MetaRefinementAgent only simulates improvement by generating placeholder diffs. We hope to replace this with genuine optimisation based on real performance metrics—contributions are warmly welcomed.
  • Note: The alpha_agi_business_3_v1 demo is intentionally left out of the published package. Clone this repository to run it from source.
USE_GPU PyTorch wheel URL
True https://download.pytorch.org/whl/cu118
False https://download.pytorch.org/whl/cpu

4.1 · [α-ASI World-Model Demo 👁️✨](

https://github.com/MontrealAI/AGI-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/alpha_asi_world_model)

Paper: [Multi-Agent AGENTIC α-AGI World-Model Demo 🥑](https://github.com/MontrealAI/AGI-Alpha- Agent-v0/blob/main/alpha_factory_v1/demos/alpha_asi_world_model/Alpha_ASI_World_Model.pdf)

┌──────────────────────────────── Alpha-Factory Bus (A2A) ───────────────────────────────┐
│                                                                                        │
│   ┌──────────────┐   curriculum   ┌───────────┐   telemetry   ┌────────────┐          │
│   │ StrategyAgent│───────────────►│ Orchestr. │──────────────►│   UI / WS  │          │
│   └──────────────┘                │  (loop)   │◄──────────────│  Interface │          │
│          ▲  ▲                     └───────────┘    commands   └────────────┘          │
│          │  │ new_env/reward                     ▲                                   │
│   plans  │  │ loss stats                        │ halt                              │
│          │  └──────────────────────┐            │                                   │
│   ┌──────┴───────┐   context       │            │                                   │
│   │ ResearchAgent│───────────────► Learner (MuZero) ◄─ SafetyAgent (loss guard)      │
│   └──────────────┘                │   ▲                                             │
│              code patches         │   │                                             │
│   ┌──────────────┐                │   │ gradients                                   │
│   │ CodeGenAgent │────────────────┘   │                                             │
│   └──────────────┘                    │                                             │
│                                       ▼                                             │
│                            POET Generator → MiniWorlds (env pool)                    │
└────────────────────────────────────────────────────────────────────────────────────────┘

4.2 · [🏛️ Large‑Scale α‑AGI Business 3 Demo 👁️✨ — Omega‑Grade Edition](

https://github.com/MontrealAI/AGI-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/alpha_agi_business_3_v1)

Alpha‑Factory v1 → Ω‑Lattice v0
Transmuting cosmological free‑energy gradients into compounding cash‑flows.

Multi‑Scale Energy‑Landscape Diagram:

flowchart TB
  subgraph Macro["Macro‑Finance Δβ"]
    FIN[FinanceAgent]:::agent
    ENE[EnergyAgent]:::agent
  end
  subgraph Meso["Supply‑Chain ΔS"]
    MFG[ManufacturingAgent]:::agent
    LOG[LogisticsAgent]:::agent
  end
  subgraph Micro["Bio/Chem ΔH"]
    BIO[BiotechAgent]:::agent
    MAT[MaterialsAgent]:::agent
  end
  FIN & ENE -->|β feed| ORC
  MFG & LOG -->|entropy ΔS| ORC
  BIO & MAT -->|latent ΔH| ORC
  classDef agent fill:#cffafe,stroke:#0369a1;
Loading

Cells with (Δ\mathcal F < 0) glow 🔵 on Grafana; Ω‑Agents race to harvest.


5 · Memory & Knowledge Fabric 🧠

[Event] --embedding--> PGVector DB
                   \--edge--> Neo4j (CAUSES, SUPPORTS, RISK_OF)
  • Agents query mem.search("supply shock beta>0.2")
  • Planner asks Neo4j: MATCH (a)-[:CAUSES]->(b) WHERE b.delta_alpha > 5e6 RETURN path
  • SQLite vector store fallback requires numpy
  • Realistic operation also relies on pandas

6 · 5‑Minute Quick‑Start 🚀

This guide assumes the repository is cloned at v0.1.0-alpha. The walkthrough requires the numpy, yaml and pandas packages which check_env.py installs automatically when run with --auto-install.

git clone --branch v0.1.0-alpha https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git
cd AGI-Alpha-Agent-v0
./quickstart.sh --preflight   # optional environment check
python check_env.py --auto-install  # verify & auto-install deps (10 min timeout)
# Install heavy optional packages such as openai_agents, gymnasium and google_adk.
# Running tests without these extras will skip or fail the modules that depend on
# them. Use ALPHA_FACTORY_FULL=1 with check_env.py to ensure they install. See
# `tests/README.md` for detailed instructions.
ALPHA_FACTORY_FULL=1 python check_env.py --auto-install
# Install runtime dependencies
pip install -r requirements.lock
# (If this fails with a network error, create a wheelhouse and rerun
#  with --wheelhouse <path> or place the wheels under ./wheels)
# Build a wheelhouse if the machine has no internet access:
#   ./scripts/build_offline_wheels.sh
./quickstart.sh               # creates venv, installs deps, launches
# Use `--wheelhouse /path/to/wheels` to install offline packages when
# the host has no internet access. The setup script automatically
# sets `WHEELHOUSE` to `./wheels` when that directory exists. When
# working offline, run `python check_env.py --auto-install --wheelhouse
# /path/to/wheels` to verify and install packages. The setup script
# exits with a message if neither network nor a wheelhouse are available.
# Example offline workflow:
#   export WHEELHOUSE=$(pwd)/wheels
#   python check_env.py --auto-install --wheelhouse "$WHEELHOUSE"
#   WHEELHOUSE=$WHEELHOUSE ./quickstart.sh
#   WHEELHOUSE=$WHEELHOUSE pytest -q
# Open http://localhost:8000/docs in your browser
# Alternatively, ``python alpha_factory_v1/quickstart.py`` provides the same
# workflow on Windows and other systems without Bash.

# Deploy instantly with Docker (prebuilt image)
docker run --pull=always -p 8000:8000 ghcr.io/montrealai/alpha-factory:latest

# Pull a specific build by commit SHA
docker run --pull=always -p 8000:8000 ghcr.io/montrealai/alpha-factory:<commit>

# The `alpha-factory` CLI also works when the package is installed:
# A short warning is printed before startup.
#   pip install -e .
#   alpha-factory --list-agents
#   alpha-asi-demo --demo   # launch the α‑ASI world‑model UI
#   alpha-agi-insight-v1 orchestrator   # run the Insight orchestrator
#
# Or install directly from GitHub for a quick test:
#   pip install git+https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git@v0.1.0-alpha
#   alpha-factory --list-agents

# Automated one-click setup (builds & starts Docker stack)
./alpha_factory_v1/scripts/one_click_install.sh --deploy

# Verify the Ω‑Lattice demo locally
python alpha_factory_v1/demos/alpha_agi_business_3_v1/alpha_agi_business_3_v1.py --loglevel info
# The entrypoint automatically verifies dependencies via `check_env.py`.

Adjust alpha_factory_v1/demos/alpha_asi_world_model/config.yaml to tune the world-model loop. Key options include env_batch (parallel environments), hidden (latent state size) and mcts_simulations (MCTS rollouts per action).

Insight Browser Demo

A browser-only Pareto explorer lives under alpha_factory_v1/demos/alpha_agi_insight_v1/insight_browser_v1. Run npm run build in that directory to generate the dist/ assets (they are not stored in Git) then open dist/index.html to run the demo locally. The quick-start guide is available from the documentation and is copied to dist/insight_browser_quickstart.pdf during the build so it is available alongside the compiled assets. Set window.DEBUG = true before loading the page to expose debugging helpers such as window.pop.

For evolutionary experiments you can run the optional evolution worker container and POST a tarball of agent code to /mutate.

Docker Quickstart

Start the full stack using Docker Compose:

docker compose up --build

Browse the dashboard at http://localhost:8080.

One-Click Docker Quickstart

Run the minimal image directly:

./run_quickstart.sh

The script prints the project disclaimer, builds docker/quickstart/Dockerfile and launches the container with your .env file mounted.

The same configuration can be installed via Helm:

helm upgrade --install alpha-demo ./infrastructure/helm-chart \
  --values ./infrastructure/helm-chart/values.yaml \
  --set env.RUN_MODE=web

This deploys the services to your local Kubernetes cluster.

Generate TLS certificates for the gRPC bus using the bundled helper:

./infrastructure/gen_bus_certs.sh > .env.bus
source .env.bus

The script prints AGI_INSIGHT_BUS_CERT, AGI_INSIGHT_BUS_KEY and AGI_INSIGHT_BUS_TOKEN which you can append to your .env file.

.env Setup & Security

Before running the orchestrator, copy alpha_factory_v1/.env.sample to .env and replace all placeholder values with strong secrets. The sample sets NEO4J_PASSWORD=REPLACE_ME as a placeholder—generate a random password for services like Neo4j and Postgres using openssl rand -base64 18 or a similar tool and never deploy with the defaults. The orchestrator will refuse to start if NEO4J_PASSWORD remains REPLACE_ME or is missing. Set API_TOKEN to a strong secret so that the REST API can authenticate incoming requests. Clients must send Authorization: Bearer <token>. The server aborts if API_TOKEN equals REPLACE_ME_TOKEN.

API Token Requirement

Before starting the API server or running the test suite, ensure API_TOKEN is set to a non-default value. The examples in tests/test_api_status.py use test-token as a reference token for local runs. Use API_RATE_LIMIT to limit requests per minute per IP (default 60). If more than 5% of requests return HTTP 429 within a minute, the server calls utils.alerts.send_alert to report excessive throttling. Avoid storing private keys directly in .env. Instead set AGI_INSIGHT_SOLANA_WALLET_FILE to a file containing your hex-encoded wallet key and keep that file readable only by the orchestrator. To enable secure gRPC transport set AGI_INSIGHT_BUS_CERT, AGI_INSIGHT_BUS_KEY and AGI_INSIGHT_BUS_TOKEN. If these values are omitted and AGI_INSIGHT_ALLOW_INSECURE=1, the bus starts without TLS. See the documentation for instructions and example volume mounts.

.env.sample notes that paths on Windows may require quotes (e.g., C:\\path\\to\\file).

Supported Environment Variables

Variable Default Purpose
OPENAI_API_KEY (empty) API key for hosted models. Offline mode is used when empty.
OPENAI_TIMEOUT_SEC 30 Timeout for OpenAI API requests in seconds.
NO_LLM 0 Set to 1 to skip the LLM planner even when OPENAI_API_KEY is provided.
ALPHA_ASI_LLM_MODEL gpt-4o-mini Planner model name used by the world model demo.
ALPHA_ASI_SEED 42 Deterministic RNG seed for the demo (can also be set via general.seed in config.yaml).
ALPHA_ASI_MAX_STEPS 100000 Learner steps before auto-stop.
ALPHA_ASI_BUFFER_LIMIT 50000 Replay-buffer length.
ALPHA_ASI_TRAIN_BATCH 128 SGD mini-batch size.
ALPHA_ASI_MAX_GRID 64 Safety clamp on generated mazes.
ALPHA_ASI_HOST 0.0.0.0 FastAPI bind address for the demo.
ALPHA_ASI_PORT 7860 FastAPI port for the demo.
NEO4J_PASSWORD REPLACE_ME Database password required by the orchestrator.
RUN_MODE api Launch mode for Compose or Helm (api, cli, web).
PORT 8000 REST API port.
AGI_INSIGHT_OFFLINE 0 Set to 1 to force local inference models.
AGI_INSIGHT_BUS_PORT 6006 gRPC bus port used by the demo.
AGI_INSIGHT_LEDGER_PATH ./ledger/audit.db Path to the local audit ledger.
AGI_INSIGHT_SECRET_BACKEND (empty) Set to vault, aws or gcp to load secrets from an external manager.
VAULT_ADDR/VAULT_TOKEN (empty) Connection details for HashiCorp Vault when using the vault backend.
AWS_REGION/OPENAI_API_KEY_SECRET_ID (empty) AWS Secrets Manager region and secret ID when using the aws backend.
GCP_PROJECT_ID/OPENAI_API_KEY_SECRET_ID (empty) GCP project and secret name when using the gcp backend.
AGI_INSIGHT_BUS_CERT (empty) Path to the gRPC bus certificate.
AGI_INSIGHT_BUS_KEY (empty) Private key matching AGI_INSIGHT_BUS_CERT.
AGI_INSIGHT_BUS_TOKEN (empty) Shared secret for bus authentication.
AGI_INSIGHT_ALLOW_INSECURE 0 Set to 1 to run the bus without TLS when no certificate is provided.
API_TOKEN REPLACE_ME_TOKEN Bearer token required by the REST API. Startup fails if unchanged.
API_CORS_ORIGINS * Comma-separated list of allowed CORS origins.
SANDBOX_CPU_SEC 2 CPU time limit for sandboxed code.
SANDBOX_MEM_MB 256 Memory cap for sandboxed code in MB.
MAX_RESULTS 100 Maximum stored simulation results.
MAX_SIM_TASKS 4 Maximum concurrent simulation tasks.
IPFS_GATEWAY https://ipfs.io/ipfs Base URL for fetching pinned Insight demo runs. Not used for asset downloads.
HF_GPT2_BASE_URL https://huggingface.co/openai-community/gpt2/resolve/main Base URL for the GPT‑2 checkpoints.
PYODIDE_BASE_URL https://cdn.jsdelivr.net/pyodide/v0.28.0/full Base URL for the Pyodide runtime files.
FETCH_ASSETS_ATTEMPTS 3 Download retry count for fetch_assets.py.
FETCH_ASSETS_BACKOFF 1 Base delay between retries in seconds.
OTEL_ENDPOINT (empty) OTLP endpoint for anonymous telemetry.
SKIP_WEBKIT_TESTS (empty) Skip WebKit browser tests when set.
ALPHA_FACTORY_ENABLE_ADK false Set to true to start the Google ADK gateway.
ALPHA_FACTORY_ADK_PORT 9000 Port for the ADK gateway when enabled.
ALPHA_FACTORY_ADK_TOKEN (empty) Optional auth token for the ADK gateway.

Troubleshooting Asset Downloads

If scripts/fetch_assets.py or npm run fetch-assets returns 401 or 404, download the checkpoint directly:

python scripts/download_hf_gpt2.py models/gpt2
# Or fetch manually from Hugging Face
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/pytorch_model.bin
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/vocab.json
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/merges.txt
curl -O https://huggingface.co/openai-community/gpt2/resolve/main/config.json

For a production-ready ADK setup see PRODUCTION_GUIDE.md.

Finance Demo Quick‑Start

Launch the finance alpha demo directly from your terminal:

curl -L https://raw.githubusercontent.com/MontrealAI/AGI-Alpha-Agent-v0/main/alpha_factory_v1/demos/finance_alpha/deploy_alpha_factory_demo.sh | bash

The script pulls the signed demo container, runs a BTC/GLD strategy, prints open positions and P&L, and exposes the trace‑graph UI at http://localhost:${TRACE_WS_PORT}.

Need a different pair or port? Use environment variables: STRATEGY=my_pair PORT_API=8001 TRACE_WS_PORT=9000 bash deploy_alpha_factory_demo.sh

No GPU → falls back to GGML Llama‑3‑8B‑Q4. No OPENAI_API_KEY → switches to local SBERT + heuristics. AF_LLM_CACHE_SIZE caps in-memory LLM cache entries (default 1024). AF_PING_INTERVAL sets the ping frequency in seconds (default 60, minimum 5). AF_DISABLE_PING_AGENT=true disables the built‑in ping agent.


6.1 · Running Tests 🧪

Unit tests can be executed with the bundled helper script:

python -m alpha_factory_v1.scripts.run_tests

Always run python check_env.py --auto-install beforehand so optional dependencies like openai_agents and gymnasium are present. Use ALPHA_FACTORY_FULL=1 to install heavy extras.

The helper validates the target directory, prefers pytest when available and otherwise falls back to unittest. Ensure all tests pass before deploying changes.

Install the optional test dependencies with:

pip install -r requirements-dev.txt
pip install -r requirements.lock  # pinned versions for deterministic setup
pip install -r alpha_factory_v1/backend/requirements-lock.txt  # includes RDKit

Install the project in editable mode so tests resolve imports:

pip install -e .
python check_env.py --auto-install  # times out after 10 minutes
# Install heavier extras so tests needing torch or faiss work:
ALPHA_FACTORY_FULL=1 python check_env.py --auto-install

The run_tests helper automatically executes python check_env.py --auto-install before running pytest. When offline, set WHEELHOUSE or pass --wheelhouse <dir> so packages install from the local wheel cache. The repository ships with a wheels/ directory that can be used as this cache. The full test suite relies on optional packages including numpy, torch, pandas, prometheus_client, gymnasium, playwright, httpx, uvicorn, git, hypothesis and requests_mock.

Tests that depend on optional heavy packages skip automatically when those libraries are missing. Set environment variables like SKIP_WEBKIT_TESTS=1 or PYTEST_NET_OFF=1 to bypass browser or network tests if the necessary dependencies aren't installed.

Wheelhouse Setup

Tests install packages from PyPI unless a local wheelhouse is provided. Build one from requirements.lock and point WHEELHOUSE to it before verifying the environment and running the suite:

mkdir -p wheels
pip wheel -r requirements.lock -w wheels
export WHEELHOUSE=$(pwd)/wheels
python check_env.py --auto-install --wheelhouse "$WHEELHOUSE"
WHEELHOUSE="$WHEELHOUSE" pytest -q

If network access is unavailable and the variable is unset these commands fail instead of falling back to PyPI.

Offline or Restricted Environments

Run ./scripts/build_offline_wheels.sh to populate a wheelhouse on a machine with internet access, then set WHEELHOUSE=<path> before executing the tests so dependencies install from this local cache. If npx playwright install fails to download WebKit, set SKIP_WEBKIT_TESTS=1 so browser checks skip gracefully.

Test Runtime

Running pytest may take several minutes on the first run while caches are created. Execute the suite in verbose mode to see ongoing progress:

pytest -vv

After completion pytest prints a summary such as ### passed in 120.00s.

The suite includes tests/test_api_rate_limit.py which spins up api_server.app with API_RATE_LIMIT=2 and verifies that exceeding the limit returns HTTP 429.

6.2 · Marketplace Demo Example 🛒

A minimal snippet queues the sample job once the orchestrator is running:

alpha-factory --enabled finance,manufacturing &
python - <<'PY'
import subprocess, time
from alpha_factory_v1.demos import alpha_agi_marketplace_v1 as market
time.sleep(5)
subprocess.run(["bash", str(market.POST_JOB_SCRIPT), str(market.SAMPLE_JOB)], check=True)
marketplace_args = ["python", "-m", "alpha_factory_v1.demos.alpha_agi_marketplace_v1.marketplace", str(market.SAMPLE_JOB)]
subprocess.run(marketplace_args, check=True)
PY

6.2 · Cross-Industry Demo Quick‑Start 🌐

Clone the stable v0.1.0-alpha release:

git clone --branch v0.1.0-alpha https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git
cd AGI-Alpha-Agent-v0/alpha_factory_v1/demos/cross_industry_alpha_factory
# Set AUTO_COMMIT=1 to save generated assets back to the repo
./deploy_alpha_factory_cross_industry_demo.sh

6.3 · Signing Agent Wheels 🔑

Sign wheels dropped into $AGENT_HOT_DIR with the project ED25519 key. You need OpenSSL to create and verify signatures. Install it with brew install openssl on macOS or from the OpenSSL Windows binaries. Generate <wheel>.whl.sig via:

openssl dgst -sha512 -binary <wheel>.whl |
  openssl pkeyutl -sign -inkey agent_signing.key |
  base64 -w0 > <wheel>.whl.sig

Keep <wheel>.whl.sig next to the wheel in $AGENT_HOT_DIR.

Verify the signature (PowerShell example):

Get-Content <wheel>.whl -Encoding Byte |
  openssl dgst -sha512 -binary |
  openssl pkeyutl -verify -pubin -inkey $env:AGENT_WHEEL_PUBKEY -sigfile <wheel>.whl.sig

Add the base64 signature to _WHEEL_SIGS in alpha_factory_v1/backend/agents/__init__.py. Wheels failing verification are ignored.

6.4 · Web Dashboard Quick-Start 📊

Launch the local web interface:

uvicorn alpha_factory_v1.demos.alpha_agi_insight_v1.src.interface.api_server:app --reload
streamlit run alpha_factory_v1/demos/alpha_agi_insight_v1/src/interface/web_app.py
# React client
cd alpha_factory_v1/demos/alpha_agi_insight_v1/src/interface/web_client
npm ci          # use the lock file for reproducible installs
npm run dev       # http://localhost:5173
# build production assets
npm run build
python -m http.server --directory dist 9000

Alternatively run inside Docker:

# build the web client first so `dist/` exists
make build_web
# regenerate protobuf modules and Go stubs
./tools/gen_proto_stubs.sh  # updates alpha_factory_v1/core/utils/a2a_pb2.py and tools/go_a2a_client/a2a.pb.go
make compose-up  # builds and waits for healthy services

Run ./tools/gen_proto_stubs.sh whenever alpha_factory_v1/core/utils/a2a.proto changes to keep the Python and Go stubs up to date. Open http://localhost:8080 in your browser. When RUN_MODE=web, the container serves the static files from alpha_factory_v1/demos/alpha_agi_insight_v1/src/interface/web_client/dist using python -m http.server. The FastAPI demo also mounts this folder at / when present so the dashboard is reachable without additional tooling.

Once running, Docker Compose marks the services healthy when:

  • http://localhost:8000/healthz returns status 200 for the orchestrator container.
  • http://localhost:8000/status exposes agent heartbeats and restart counts. Use alpha-agi-insight-v1 agents-status to view the same data from the CLI.
  • http://localhost:8080/ returns status 200 for the web container.

The dashboard now plots a 3‑D scatter chart of effectiveness vs. risk vs. complexity from the final population.

If Streamlit isn't installed or you're running on a headless server, use:

python -m alpha_factory_v1.demos.alpha_agi_insight_v1.src.interface.minimal_ui --text

to display the forecast results directly in the console.


7 · Deployment Recipes 🍳

The repository bundles a lightweight edge_runner.py helper for running Alpha‑Factory on air‑gapped or resource‑constrained devices. The script forwards to alpha_factory_v1.edge_runner and exposes additional flags like --cycle, --loglevel and --version. It prints the same warning as the main CLI before launching.

Build the demo containers locally:

cp .env.sample .env  # fill in NEO4J_PASSWORD, API_TOKEN and optional PINNER_TOKEN
chmod 600 alpha_factory_v1/.env
cd infrastructure
docker build -t alpha-demo .
docker compose up -d
# Dashboard available at <http://localhost:8080>

The Compose stack restricts the agents worker using Docker resource limits. The agents service runs with mem_limit: 8g, pids_limit: 512 and network_mode: none to prevent outbound traffic.

The Helm chart under infrastructure/helm-chart mirrors this Compose setup:

helm upgrade --install alpha-demo ./infrastructure/helm-chart \
  --values ./infrastructure/helm-chart/values.yaml \
  --set env.RUN_MODE=web
# Enable persistent storage for the audit ledger
#   --set persistence.enabled=true --set persistence.size=5Gi
# → browse to <http://localhost:8080>

values.example.yaml demonstrates typical overrides such as API tokens, service ports and replica counts.

The Helm charts ship with placeholders like NEO4J_PASSWORD and adminPassword set to REPLACE_ME. Replace these with strong secrets in values.yaml or via --set before deploying.

Terraform scripts in infrastructure/terraform provide GCP and AWS examples. Update the placeholder image and networking variables, then initialise and apply:

cd infrastructure/terraform
terraform init
terraform apply
Target Command Notes
Docker Compose docker compose up -d Web UI on localhost:8080
Helm (K8s) helm install af helm/alpha-factory --set env.RUN_MODE=web
AWS Fargate ./infra/deploy_fargate.sh set container_image & subnets
IoT Edge python edge_runner.py --agents manufacturing,energy Jetson Nano

🚀 Deploying securely

See the documentation for TLS setup, API tokens and Vault usage. Mount secrets via Docker or Kubernetes and never commit them.


8 · Governance & Compliance ⚖️

  • MCP envelopes (SHA‑256, ISO‑8601, policy hash)
  • Red‑Team Suite fuzzes prompts & actions
  • Attestations — W3C Verifiable Credentials at every Actuator call

9 · Observability 🔭

Signal Sink Example
Metrics Prometheus alpha_pnl_realised_usd
Traces OpenTelemetry trace_id
Dashboards Grafana alpha-factory/trade-lifecycle.json

Prometheus scrapes metrics from the API server at /metrics.

By default traces and metrics print to stdout. To export to a collector such as Jaeger, set OTEL_EXPORTER_OTLP_ENDPOINT and start Jaeger locally:

docker run -p 16686:16686 -p 4317:4317 jaegertracing/all-in-one

Set OTEL_ENDPOINT to enable anonymous dashboard telemetry. Users are prompted for consent before any metrics are sent.

Telemetry Queue

Anonymous usage metrics are buffered in the browser under the telemetryQueue key in localStorage. Each record includes:

  • ts – the timestamp when the entry was recorded.
  • session – a deterministic SHA‑256 hash identifying the session.
  • generations – how many runs were executed.
  • shares – how many times results were shared.

When the browser is online the queue is flushed to OTEL_ENDPOINT using navigator.sendBeacon with a fetch fallback. The queue holds at most 100 entries and is persisted across page loads until sent. No personal data or IP addresses are stored.

Telemetry can be disabled from the Analytics panel by clicking Disable telemetry. Clearing the telemetryConsent and telemetryQueue entries in browser storage also stops all transmissions.


10 · Safety & Security 🛡️

The policy runbook outlines sandbox resource limits, timeout behaviour, required human review and rollback steps. Operational tips for the governance module reside in the documentation.


11 · Extending the Mesh 🔌

from backend.agents.base import AgentBase

class MySuperAgent(AgentBase):
    NAME = "super"
    CAPABILITIES = ["telemetry_fusion"]
    COMPLIANCE_TAGS = ["gdpr_minimal"]

    async def run_cycle(self):
        ...

# setup.py entrypoint
[project.entry-points."alpha_factory.agents"]
super = my_pkg.super_agent:MySuperAgent

pip install . → orchestrator hot‑loads at next boot.


12 · Troubleshooting 🛠️

Symptom Cause Fix
ImportError: faiss FAISS missing pip install faiss-cpu
Agent quarantined exceptions Check logs, clear flag
Kafka refuse broker down unset ALPHA_KAFKA_BROKER

13 · Roadmap 🛣️

  1. RL‑on‑Execution — slippage‑aware order routing
  2. Federated Mesh — cross‑org agent exchange via ADK federation
  3. World‑Model Audits — interpretable probes of latents
  4. Industry Packs — Health‑Care, Gov‑Tech
  5. Provable Safety ℙ — Coq proofs for Actuators

14 · Credits 🌟

Vincent Boucher—pioneer in AI and President of MONTREAL.AI since 2003—dominated the OpenAI Gym with AI Agents in 2016 and unveiled the seminal “Multi‑Agent AI DAO” in 2017.

Our AGI ALPHA AGENT, fuelled by the strictly‑utility $AGIALPHA token, now taps that foundation to unleash the ultimate α‑signal engine.

AGIALPHA Token

  • Address: 0xa61a3b3a130a9c20768eebf97e21515a6046a1fa
  • Decimals: 18 (ERC‑20 standard; 1 token = 1e18 base units)
  • Config defaults: token.config.js pins the token wiring for builds and tests; override with AGIALPHA_ADDRESS / AGIALPHA_DECIMALS environment variables when deploying to alternate networks.

ERC‑20 Approvals

Staking and job escrow pull funds via transferFrom, so each account must approve the StakeManager contract before staking or posting a job. $AGIALPHA uses 18 decimals, meaning 1e18 represents one token.

# Allow the StakeManager to move 100 AGIALPHA for your stake
cast send 0xa61a3b3a130a9c20768eebf97e21515a6046a1fa \
  "approve(address,uint256)" $STAKEMANAGER 100e18

# Authorize 50 AGIALPHA to be locked as job escrow
cast send 0xa61a3b3a130a9c20768eebf97e21515a6046a1fa \
  "approve(address,uint256)" $STAKEMANAGER 50e18

Replace $STAKEMANAGER with the deployed contract address.

15 · License

This project is distributed under the Apache 2.0 license. All community members are expected to follow our Code of Conduct. Please report security issues via the process outlined in our Security Policy.

Release Tweet

🚀 New Alpha-Factory release! Offline dashboard, responsive UI and automated visual tests powered by Percy.

16 · Final Note

Please ensure all usage and contributions align with the project's Apache 2.0 license.

Made with ❤️ by the Alpha‑Factory Agentic Core Team — forging the tools that forge tomorrow.

About

♾️ TRANSFORMATIONAL META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡ → Out-Evolve ♾️

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

310 stars

Watchers

10 watching

Forks

Releases

Packages

Used by

Contributors

Languages