Skip to content

cipher813/alpha-engine-research

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

465 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

alpha-engine-research

Part of Nous Ergon — Autonomous Multi-Agent Trading System. Repo and S3 names use the underlying project name alpha-engine.

Part of Nous Ergon Python LangGraph Anthropic Claude License: MIT Phase 2 · Reliability

Multi-agent investment-research pipeline. Six sector teams, a CIO, and a macro economist scan the S&P 500+400 weekly, maintain rolling investment theses, and emit signals.json for the rest of the system. Built on LangGraph with Anthropic Claude (Haiku per-team, Sonnet for synthesis).

System overview, Step Function orchestration, and module relationships live in alpha-engine-docs. Code tour and key files live in OVERVIEW.md.

What this does

  • Six sector teams (Tech, Healthcare, Financials, Industrials, Consumer, Defensives) run in parallel via LangGraph Send() fan-out. Each team: quant ReAct → qual ReAct (with RAG retrieval over SEC filings + earnings + theses) → peer review → 2–3 ranked recommendations + thesis update.
  • Macro economist runs in parallel with a reflection loop, producing market regime + per-sector ratings that scale recommendations downstream.
  • CIO evaluates every recommendation in a single Sonnet batch call against a 4-dimension rubric and gates new entrants per a configurable cap.
  • LLM-as-judge layer scores agent outputs at key stages against rubric prompts. Every decision is captured to S3 with prompt metadata + cost telemetry for replay and audit.

Phase 2 measurement contribution

This is where every agent decision in the system happens. Each one is captured as a structured artifact — prompt id + version + hash, full prompt context, input snapshot, agent output, and cost — replayable, auditable, and attributable to a specific prompt revision. The LLM-as-judge layer scores agent quality at key stages against rubric prompts. Together these are the substrate that lets Phase 3 measure whether prompt or model changes actually improve agent quality.

Architecture

flowchart LR
    Data[Data + RAG<br/>universe · macro · filings] --> Teams[6 sector teams<br/>quant → qual → peer review]
    Data --> Macro[Macro economist<br/>regime + sector ratings]
    Teams --> CIO[CIO synthesis<br/>Sonnet · 4-dim rubric<br/>entrant gate]
    Macro --> CIO
    CIO --> Out[signals.json<br/>thesis history<br/>decision artifacts]
Loading

Decision-artifact capture wraps every LLM call site via LoadedPrompt (frontmatter-versioned prompts, sha256 body hash) and a track_llm_cost ContextVar accumulator that stamps token counts + cost on each invocation.

Configuration

This repo is public. Agent prompts, scoring weights, universe configuration, and proprietary scoring formulas are gitignored locally and stored in the private alpha-engine-config repo. Architecture and approach are public; specific values are private.

Sister repos

Module Repo
Executor alpha-engine
Data alpha-engine-data
Predictor alpha-engine-predictor
Backtester alpha-engine-backtester
Dashboard alpha-engine-dashboard
Library alpha-engine-lib
Docs alpha-engine-docs

License

MIT — see LICENSE.

About

Nous Ergon — LangGraph multi-agent research pipeline: rolling investment theses, S&P 900 scanner, composite signal scoring

Topics

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors