awesome-trading-agents

Awesome Trading Agents collects open-source projects where LLMs help research markets, make trading decisions, or connect agents to market data and execution tools. The list focuses on three building blocks: Agents, MCPs, and Skills. It does not try to cover classic quant libraries, time-series models, or reinforcement-learning trading bots; those are better served by georgezouq/awesome-ai-in-finance and wilsonfreitas/awesome-quant. Entries are selected for public code or artifacts, clear LLM-driven behavior, recent activity, useful documentation, a distinct role, and visible adoption. Stewarded by the LLMQuant community.

[!TIP] If you only read three:

• Agents — TauricResearch/TradingAgents · virattt/ai-hedge-fund · HKUDS/AI-Trader
• MCPs — alpacahq/alpaca-mcp-server · krakenfx/kraken-cli · financial-datasets/mcp-server
• Skills — tradermonty/claude-trading-skills · himself65/finance-skills · RKiding/Awesome-finance-skills

[!NOTE] Dates are not shown after every item. We still check recent activity before adding or updating a project; the README only keeps details that help readers choose a project, such as official status, forks, or useful pairings.

Contents

• Agents
  • Multi-agent trading systems
  • Single-agent end-to-end traders
  • Research / equity-research copilots
  • Real-money / competition experiments
  • Prediction-market specialists
  • Benchmarks & evaluations
  • Strategy coding / self-improving agents
• MCPs
  • Market data / data providers
  • Brokerage / exchange trading
  • Research tools / analysis
  • TradingView bridge
  • Prediction markets
  • Strategy / backtesting platforms
• Skills
  • Equity research
  • Crypto / DeFi / on-chain
  • Strategy coding & backtesting
  • Brokerage execution & portfolio
• Resources
  • Papers
  • Learn
• Related awesome lists

Agents

Agents are projects where an LLM is part of the actual research or trading decision. This includes analyst teams, single-agent traders, research copilots, live trading experiments, benchmarks, and tools that write or improve strategies. The TradingAgents forks are listed at the same level as the original project so the section stays easy to scan.

Multi-agent trading systems

• TauricResearch/TradingAgents - Multi-agent trading framework where analysts, bull/bear researchers, a trader, risk control, and a portfolio manager debate before making a decision; built with LangGraph.
• hsliuping/TradingAgents-CN - Chinese-localised TradingAgents fork tuned for A-shares; Tushare / AkShare data sources + Chinese-language reports + A-share regulatory context. (← fork of TauricResearch/TradingAgents.)
• KylinMountain/TradingAgents-AShare - A-share rewrite; 15 agents + visual UI + OpenClaw / Claude Code integration + one-click Docker deploy. (← fork of TauricResearch/TradingAgents.)
• oficcejo/aiagents-stock - A-share multi-agent analyst team with dragon-and-tiger list tracking, sector-rotation alerts, and a miniqmt execution hook. (← inspired by TradingAgents.)
• HKUDS/AI-Trader - "Agent-native trading platform"; any AI agent (OpenClaw / nanobot / Claude Code / Codex / Cursor) registers via SKILL.md and trades live on AI4trade.ai; multi-asset + copy-trading + cross-platform sync.
• ValueCell-ai/valuecell - Community finance workspace with research, strategy, and news agents; connects to Binance, OKX, and Hyperliquid; includes macOS and Windows desktop apps.
• AI4Finance-Foundation/FinRobot - AI4Finance Foundation's open-source finance AI agent platform; useful for academic-style stock research, market forecasting, and report generation.
• HKUDS/Vibe-Trading - Personal multi-agent finance workspace from HKUDS Lab; bundles Skills, MCP tools, and swarm presets across A-shares, HK, US, crypto, futures, and forex.
• brokermr810/QuantDinger - Open-source AI quant-trading platform; combines multi-agent research, backtesting, live trading, and multi-exchange routing.
• Lumiwealth/lumibot - Backtestable AI trading-agent/team runtime with research, debate, risk, and memory in one backtest/paper/live strategy loop.

[!NOTE] Also useful here: guangxiangdebizi/TradingAgents-MCPmode turns TradingAgents-style research into MCP tools. The full entry is in MCPs · Research tools / analysis.

Also see: chrisworsey55/atlas-gic is listed under single-agent traders, but it is relevant here because it replaces debate with continuous self-research.

Single-agent end-to-end traders

• virattt/ai-hedge-fund - Widely forked LLM-driven equity-trading repo; analyst personas (Buffett / Munger / Cathie Wood) propose, the portfolio manager decides.
• TraderAlice/OpenAlice - "Your one-person Wall Street"; single agent covering research → entry → hold → exit; Claude Agent SDK + Trading-as-Git approval workflow + cross-asset UTA account design.
• NoFxAiOS/nofx - Self-hosted LLM trading terminal; models decide and explain while a Go runtime enforces hard risk limits across nine exchanges.
• chrisworsey55/atlas-gic - General Intelligence Capital's self-improving trading agent; focuses on continuous self-research rather than agent debate.
• [Gajesh2007/ai-trading-agent](https://github.c