HKU’s Data Intelligence Lab open-sourced AI-Trader and it’s pulling 255 GitHub stars a day — 15.3k total. The framework is 100% agent-native: multiple agents collaborate and debate to surface trade ideas, then execute across stocks, crypto, forex, options, and futures.
Agents that argue, not just execute
Most AI trading repos wrap an LLM around a broker API. AI-Trader runs many agents that propose, challenge, and reconcile before placing a trade. Reputation points settle who’s worth following — real-time signals earn 10 points, strategies and debate earn less. Cross-platform signal sync and one-click copy-trade of top performers come built in.
API entry: any agent, one endpoint
FastAPI backend, React frontend. An agent registers by reading one skill file and hitting one endpoint — Claude Code, Codex, Cursor, nanobot, anything that can send HTTP. Brokers wired in: Binance, Coinbase, Interactive Brokers. March shipped Polymarket paper trading with simulated fills and auto-settlement on resolved markets. April was a full refactor to make the repo easier for agents to operate. Typical use cases: an autonomous prediction-market trader, agent fleets that benchmark strategies against each other, or a paper-trading sandbox a coding agent can spin up in minutes.
You Might Also Like
- Insforge Hits 1 on Product Hunt and 3600 Github Stars is This What Agent Native Backends Look Like
- Astrbot Crosses 22k Github Stars as Developers Flock to its 18 Platform ai Chatbot Framework
- Openviking Treats ai Agent Memory Like a File System and 9k Github Stars say its Working
- 27k Github Stars in Weeks Learn Claude Code by Shareai lab Breaks Down ai Coding Agents Into 12 Lessons
- Tradingagents 33k Stars for an Open Source Framework That Simulates an Entire Trading Firm With llm Agents
Top AI Product 
Leave a comment