Inspired by DeepMind’s AlphaEvolve coding agent—this project applies the same evolutionary-LLM principles to financial markets.

Autonomously discovers and back‑tests high‑performing algorithmic‑trading strategies using evolutionary LLM prompts, Backtrader, and the Papers‑With‑Backtest data ecosystem.

# Clone and install in editable mode $ git clone https://github.com/paperswithbacktest/pwb-alphaevolve.git $ cd pwb-alphaevolve $ pip install -e . # Set your OpenAI key (model "o3" required) $ export OPENAI_API_KEY=sk-... # Set your Papers‑With‑Backtest dataset (e.g. "paperswithbacktest/Stocks-Daily-Price") $ export HF_ACCESS_TOKEN=hf_

Launch the evolution controller (infinite loop)

from alphaevolve import AlphaEvolve # Initialize the system evolve = AlphaEvolve( initial_program_paths=["examples/sma_momentum.py"] ) # Run the evolution best_strategy = await evolve.run(iterations=1000) print(f"Best strategy metrics:") for name, value in best_strategy.metrics.items(): print(f" {name}: {value:.4f}")

Monitor the evolution process in real‑time using the optional Streamlit dashboard:

$ streamlit run scripts/dashboard.py

The dashboard uses Streamlit to visualize the evolution process and back‑test results.

alphaevolve/ ├── engine.py # convenience wrapper to run the evolution loop ├── evaluator/ # data loading, metrics & Backtrader evaluation ├── evolution/ # controller, patching, islands ├── llm_engine/ # prompt builder + OpenAI client ├── strategies/ # seed strategies (EVOLVE‑BLOCK markers) └── store/ # SQLite persistence scripts/ # CLI entry‑points 

Python ≥ 3.10 required.

pip install pwb-alphaevolve

Or install the bleeding‑edge version:

pip install git+https://github.com/paperswithbacktest/pwb-alphaevolve.git

• pwb-toolbox
• pwb-backtrader
• openai ≥ 1.0 (structured output)
• tqdm, pandas, numpy, pydantic

(See pyproject.toml for the full list.)

1. Fork the repo & create your feature branch (git checkout -b feat/new-feature).
2. Commit your changes (git commit -m 'feat: add something').
3. Push to the branch (git push origin feat/new-feature).
4. Open a Pull Request.

Please run black + ruff before submitting.

MIT © 2025 Contributors