Home / LLM agents & research
jason8745/llm-agent-trader
LLM-driven stock trading backtest system with web interface
What it is
A stock trading backtest system in which a large language model analyses the market and explains its decisions. It is built as a full application with a FastAPI backend and a Next.js frontend. Researchers and developers interested in how LLM agents behave in trading can run experiments through the interface. Decisions come from model output, so results vary with the model used and should be treated as experiments.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Stack | Python |
|---|---|
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +9 over the period, now 495. Gaps mean no snapshot was taken that day.
AI-powered stock trading backtesting system with LLM-based decision analysis, FastAPI backend, and Next.js frontend.
Similar tools
LLM trading research agent with multi-market backtesting
LLM multi-agent investment research framework specialized for A-shares
Open-source LLM harness for agentic trading
Multi-agent AI stock analysis with automated trading for Korea and US
Chinese open-source quant finance tutorial with AI arXiv radar
Multi-agent LLM research assistant for Chinese A-shares