#2323rd of 80 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting
ai-hedge-fund
Terminal app that paper-trades and backtests LLM-driven investor agents on stocks
- Stars
- 64.6k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
52,389 on 13 Apr 202664,631 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Python terminal app (installed as `aihf`) where LLM investor agents make trading decisions for funds you define with strategies, capital, cadence and tickers. It supports paper trading over real market days with a hash-chained ledger and an approval step, plus backtesting against a benchmark. It never places real trades and is stated to be for educational use only.
Who it is for: Developers exploring LLM-driven trading strategies in simulation
Strengths
- Installs with pipx, uv or pip; API keys are prompted for and saved to ~/.hedge-fund/.env
- Paper-trading sessions go into a hash-chained ledger, so NAV is an auditable record
- Approval step shows the exact decision before a paper trade executes; kill switch included
- Backtests replay a fund over history against a benchmark; fund definitions carry no tickers
Weaknesses
- Does not execute real trades; no broker integration
- Requires a Financial Datasets API key for prices, fundamentals and earnings
- Needs a hosted model API key; local models are not listed as supported
- Terminal UI only; no web interface or Docker image
What it needs
- no GPU
- Needs Financial Datasets API key, LLM provider API key
- Models: Anthropic, OpenAI, DeepSeek, Google, xAI
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is ai-hedge-fund open source?
Yes. Its code is on GitHub under the MIT license.
Does ai-hedge-fund need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |