85Score
TradingAgentsTauricResearch/TradingAgentsA multi-agent research desk: analyst agents argue the bull and bear case, a risk agent signs off before any trade idea moves.
★ 118k stars · Intermediate · updated 2026-10
AI Agents
AI Agent Trading Teams on GitHub | The Robot Research Desk, Graded
LLM agent teams that research, debate and propose trades, from TradingAgents to Vibe-Trading.
In plain English
A multi-agent framework is a team of AI assistants, each with a job. One reads the news, one studies the chart, one argues the bear case, and a final one makes the call.
What Should You Know Before Picking a AI Agents Repo?
The pitch is seductive: a hedge fund's research desk, rebuilt from AI agents, running on your laptop. Projects like 
Vibe-Trading and 
FinRobot show how far that idea has come, and the star counts prove people want it.
Here is the market truth. None of these teams has a public, audited track record. Several have been criticized for backtests the AI could cheat on, because the model already read the news from the period it is being tested on. That is like grading a student on a test they saw last week.
Use these as research assistants, not portfolio managers. They are excellent at building a bull and bear case fast. Let them argue. Then you decide.
Who this lane is for
- Traders who want a second opinion that argues back
- Curious builders who want to see how AI research desks work
- People comfortable editing a config file and running Python
Where to start: If you want the idea without the setup, the Claude Code skill pack is the gentlest entry. If you want the real thing, Vibe-Trading is the most active project in this lane.
AI Agents, Explained in One Picture
Every AI Agents Repo We Verified, Ranked by Community Score
- 85ScoreTradingAgentsTauricResearch/TradingAgents
84ScoreVibe-TradingHKUDS/Vibe-TradingA multi-agent research workspace from HKU with built-in backtest engines and trade-journal analysis.
★ 37k stars · Intermediate · updated 2026-10
Claude
Codex
Local models
83Score
AI Hedge Fundvirattt/ai-hedge-fundInvestor-persona agents debate a stock, then a portfolio agent makes the call. A teaching project, not a fund.
★ 64k stars · Intermediate · updated 2026-10
78ScoreFinRobotAI4Finance-Foundation/FinRobotLLM agents that draft equity research reports from filings and market data.
★ 8.3k stars · Advanced · updated 2026-10
62Score
AgenticTradingOpen-Finance-Lab/AgenticTradingA research framework for graph-coordinated trading agents with decision logs and simulated fills.
★ 787 stars · Advanced · updated 2026-10
60ScoreAI-TraderHKUDS/AI-TraderAn agent-native platform where coding agents act as market participants through a skill file.
★ 23k stars · Advanced · updated 2026-06
- No license
- Claude
- Codex
48Score
AI Trading Analyst for Claude Codezubair-trabzada/ai-trading-claudeA Claude Code skill pack that runs parallel analysis agents and outputs a research report.
★ 295 stars · Beginner · updated 2026-04
Gemini
DeepSeek
Keep reading across FullStack Alpha
- AIStockTradingBots.comWhat agentic trading really means →
- AIStockTradingBots.comTradingAgents, our full breakdown →
- AIStockTradingBots.comAI trading agent risks →
- AIStockTradingBots.comBuilding a Claude trading agent →
- AIStockPickerApps.comAI trading platforms directory →
- AIStockPickerApp.comAI stock picker claims, fact-checked →
Not ready to run code yourself? Our hands-on AI stock tool reviews on AIStockPickerApp.com score finished products on five pillars, the AI stock tools directory at AIStockPickerApps.com sorts 200+ tools by the job they do, and AIStockTradingBots.com walks through broker APIs, bot setup and backtesting step by step. Or head back to the Trading Workflows home page to match tools to your own routine and budget.
AI Agents Repos FAQ
Can multi-agent AI frameworks trade for me?
Most of them propose trades rather than place them, and none publishes an audited record of making money. Treat them as research tools and keep execution in your own hands.
Do I need an OpenAI or Anthropic API key?
Usually yes, or a local model running on your own computer. Agent teams make many AI calls per stock, so watch your usage bill.
Why are AI agent backtests unreliable?
The AI models were trained on years of real news and prices. When you test them on that same period, they may already know what happened, which makes results look better than they really are.