Out‑learn · Out‑think · Out‑design · Out‑strategise · Out‑execute
Welcome to Alpha‑Factory v1, an antifragile constellation of self‑improving agents orchestrated to spot live alpha across any industry and transmute it into compounding value.
Built atop OpenAI Agents SDK, Google ADK, the A2A protocol, and Anthropic’s Model Context Protocol, the stack operates online or fully‑air‑gapped, switching fluidly between frontier models and local fallbacks.
Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡
- Design Philosophy
- System Topology 🗺️
- World‑Model & Planner 🌌
- Agent Gallery 🖼️ (12 agents)
- Demo Showcase 🎬 (12 demos)
- Memory & Knowledge Fabric 🧠
- 5‑Minute Quick‑Start 🚀
- Deployment Recipes 🍳
- Governance & Compliance ⚖️
- Observability 🔭
- Extending the Mesh 🔌
- Troubleshooting 🛠️
- Roadmap 🛣️
- Credits 🌟
“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.
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)]
- 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.
| 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 |
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{{"📊"}}
| # | 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;
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
| Notebook | What You’ll See | Agents |
|---|---|---|
| Meta Evolution 🧬 | Agents evolve agents | TAL + WM |
| Business Builder 🏢 | Incorporate firm E2E | FIN + POL |
| Cross‑Industry Pipeline ⚙️ | Plan → Act across 4 verticals | Multi |
| Fin Momentum Bot 💹 | Live momentum execution | FIN |
| MuZero Planner ♟️ | Counterfactual rollouts | WM + FIN |
| Energy DR ⚡ | DR bidding & battery schedule | ENE |
| Supply‑Chain Optimizer 🚚 | Reduce OTIF penalties | SUP + MFG |
| Climate Sentinel 🛰️ | Auto‑hedge transition risk | CLM + FIN |
| Cyber Sentinel 🛡️ | Self‑healing repo | CYB |
| Drug‑Design Loop 💊 | Diffusion + docking walk‑through | DRG |
| Retail Pricing 🛍️ | Causal demand & markdowns | RET |
| Agent Marketplace 🌐 | P2P capability exchange | TAL |
Launch with:
jupyter lab --NotebookApp.token=''Paper: Multi-Agent AGENTIC α-AGI World-Model Demo 🥑
┌──────────────────────────────── 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) │
└────────────────────────────────────────────────────────────────────────────────────────┘
[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
git clone https://github.com/MontrealAI/AGI-Alpha-Agent-v0.git
cd AGI-Alpha-Agent-v0/alpha_factory_v1
pip install -r requirements.txt
export ALPHA_KAFKA_BROKER=localhost:9092
python -m backend.orchestrator
open http://localhost:8000/docsNo GPU → falls back to GGML Llama‑3‑8B‑Q4.
No OPENAI_API_KEY → switches to local SBERT + heuristics.
| Target | Command | Notes |
|---|---|---|
| Docker Compose | docker compose up -d |
Kafka, Prometheus, Grafana |
| Helm (K8s) | helm install af charts/alpha-factory |
SPIFFE, HPA |
| AWS Fargate | ./infra/deploy_fargate.sh |
SQS shim for Kafka |
| IoT Edge | python edge_runner.py --agents manufacturing,energy |
Jetson Nano |
- MCP envelopes (SHA‑256, ISO‑8601, policy hash)
- Red‑Team Suite fuzzes prompts & actions
- Attestations — W3C Verifiable Credentials at every Actuator call
| Signal | Sink | Example |
|---|---|---|
| Metrics | Prometheus | alpha_pnl_realised_usd |
| Traces | OpenTelemetry | trace_id |
| Dashboards | Grafana | alpha-factory/trade-lifecycle.json |
from backend.agent_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:MySuperAgentpip install . → orchestrator hot‑loads at next boot.
| 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 |
- RL‑on‑Execution — slippage‑aware order routing
- Federated Mesh — cross‑org agent exchange via ADK federation
- World‑Model Audits — interpretable probes of latents
- Industry Packs — Health‑Care, Gov‑Tech
- Provable Safety ℙ — Coq proofs for Actuators
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.
Made with ❤️ by the Alpha‑Factory Agentic Core Team — forging the tools that forge tomorrow.