GitHub Repos intermediate 3 min read May 9, 2026
Public Preview Sign in free for the full digest →

AI Hedge Fund: A 19-Agent Multi-Agent System for Stock Analysis

“58,438 developers starred a hedge fund that its own README says you should never trade with.”

AI Hedge Fund: A 19-Agent Multi-Agent System for Stock Analysis
Source · github.com

“"The pattern of specialized agents debating to reach better decisions is the feature everyone will be building in 2025." — Yuval Avidani, yuv.ai/blog/ai-hedge-fund-building-investment-teams-from-ai-agents (published Jan 5, 2026, fetched 2026-05-10)”

You know that feeling when you want to study how multiple AI agents collaborate on a decision, but every example in the docs is trivially simple — one agent, one task, no shared state to manage? Building a realistic multi-agent system means designing state passing, handling conflicting agent outputs, wiring LLM calls into a graph, streaming results to a UI, and adding risk controls — all before you can observe anything interesting. This repo gives you a working 19-agent system with investor personas, risk limits, and a React flow editor so you can study the orchestration patterns without building the plumbing. The financial domain also makes the agent outputs immediately legible: buy, hold, or sell is a clearer output than abstract task completion.

pythonllmmulti-agentlanggraphfintechopen-sourceai-agents

You open a browser, drag investor-persona agents and analysis agents onto a canvas, and connect them into a flow — deciding which analysts feed into the risk manager before the portfolio manager makes the final call. The frontend sends that graph definition via HTTP to a FastAPI backend, which resolves node identifiers to registered Python functions and hands the topology to LangGraph. LangGraph runs each agent sequentially: every agent reads the shared immutable AgentState (portfolio positions, cash balances, previous signals, market data), runs its analysis through an LLM call, and writes its verdict back to the state. The risk manager applies hard position limits after all analysts complete, then the Portfolio Manager issues the final recommendation. Results stream to your browser in real time via Server-Sent Events — you watch each agent's reasoning appear as it finishes.

01
19 pre-built agent personas — 14 investor-style agents (Buffett, Burry, Cathie Wood, Charlie Munger, Peter Lynch, Nassim Taleb, and more) plus sentiment, fundamentals, technicals, risk, and portfolio manager agents; you get a complete cast...
02
Visual graph editor — a React Flow drag-and-drop interface lets you choose which agents participate and how they connect, so you can test different orchestration topologies without editing Python
03
Real-time reasoning stream — Server-Sent Events push each agent's analysis to your browser as it completes, giving you the full reasoning chain, not just a final answer
04
8 LLM provider integrations — OpenAI, Anthropic, Groq, DeepSeek, Google Gemini, Ollama (local), xAI, and GigaChat; the --ollama flag runs the entire system locally at zero API cost
05
Deterministic risk controls — a hard position-limit layer runs before the LLM Portfolio Manager issues its final decision, preventing the model from exceeding defined risk thresholds regardless of what it generates
06
SQLAlchemy + Alembic persistence — portfolio state and trade history persist across sessions with schema migrations included, enabling backtesting scenario comparison
07
FastAPI + SSE backend with four structured event types (start, progress, complete, error) that you can wire into any frontend, not just the included React app
Who it’s for

If you're building with LangGraph or LangChain and want to study a real multi-agent orchestration pattern beyond toy examples, this repo shows you 19 coordinated agents with shared state management, SSE streaming, and a React visual editor already wired together. Also useful if you're prototyping fintech AI tooling and need a reference architecture for agent-based analysis pipelines. Not appropriate if you need production trading infrastructure — the repo has no declared license (legal ambiguity for commercial derivatives), no backtesting benchmarks showing agent outputs outperform a baseline...

Worth exploring

Worth exploring if you're learning LangGraph multi-agent patterns or building a demo of agent-based financial analysis — the architecture is well-structured, and the React + FastAPI + LangGraph stack is a clean reference for this class of system. Not ready for production use: no declared license creates legal ambiguity for commercial derivatives, no performance benchmarks exist showing the agents outperform a market baseline, ETF data integration is broken (issue #617), and LLM calls can hang indefinitely without timeouts (issue #618).

Developer playbook
Tech stack, code snippet, sentiment, alternatives.
PM playbook
Adoption angles, user fit, positioning.
CEO playbook
Traction signals, ROI, build vs buy.
Deep-dive insight
Full long-form analysis, no fluff.
Easy mode
Core idea, fast — when you need the gist.
Pro mode
Technical nuance, edge cases, tradeoffs.
Read the full digest
Go beyond the preview

Deep-dive insight, Easy and Pro modes, plus action playbooks — the full breakdown is one tap away.

Underrated tools. Unfiltered takes.

Read the full digest in the Snaplyze app for deep-dive insight, Easy and Pro modes, and the playbooks you can actually use.

Install Snaplyze →