Awesome Trading Agents

English · 简体中文

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](#agents-tradingagents) · [virattt/ai-hedge-fund](#agents-ai-hedge-fund) · [HKUDS/AI-Trader](#agents-ai-trader) > - MCPs — [alpacahq/alpaca-mcp-server](#mcps-alpaca) · [krakenfx/kraken-cli](#mcps-kraken-cli) · [financial-datasets/mcp-server](#mcps-financial-datasets) > - Skills — [tradermonty/claude-trading-skills](#skills-claude-trading-skills) · [himself65/finance-skills](#skills-finance-skills) · [RKiding/Awesome-finance-skills](#skills-alphaear)

> [!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](#agents)
• [Multi-agent trading systems](#agents-multi-agent)
• [Single-agent end-to-end traders](#agents-single-agent)
• [Research / equity-research copilots](#agents-research-copilots)
• [Real-money / competition experiments](#agents-real-money)
• [Prediction-market specialists](#agents-prediction-market)
• [Benchmarks & evaluations](#agents-benchmarks)
• [Strategy coding / self-improving agents](#agents-strategy-coding)
• [MCPs](#mcps)
• [Market data / data providers](#mcps-market-data)
• [Brokerage / exchange trading](#mcps-brokerage)
• [Research tools / analysis](#mcps-research-tools)
• [TradingView bridge](#mcps-tradingview)
• [Prediction markets](#mcps-prediction-market)
• [Strategy / backtesting platforms](#mcps-backtesting)
• [Skills](#skills)
• [Equity research](#skills-equity-research)
• [Crypto / DeFi / on-chain](#skills-crypto)
• [Strategy coding & backtesting](#skills-strategy-coding)
• [Brokerage execution & portfolio](#skills-brokerage)
• [Resources](#resources)
• [Papers](#resources-papers)
• [Learn](#resources-learn)
• [Related awesome lists](#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.
• The-Swarm-Corporation/AutoHedge - "Spin up an autonomous hedge fund in minutes"; applies the Swarms framework to market analysis, risk, and execution; CLI / SDK first.
• olaxbt/ai-market-maker - Agentic crypto hedge-fund stack with specialist agents, Risk Guard, backtests, paper trading, and OpenClaw packaging.

• ginlix-ai/LangAlpha - "Claude Code for finance"; LangChain + LangGraph multi-agent investment workbench; integrates Agents · MCPs · Skills in one repo.
• ygwyg/MAHORAGA - TypeScript crypto-trading agent focused on social sentiment analysis and adaptive learning; useful if you want a TypeScript implementation.
• FinStep-AI/ContestTrade - Multi-agent trading system where agents compete internally before one view is selected for the final decision.
• 51bitquant/ai-hedge-fund-crypto - Crypto-focused fork of virattt/ai-hedge-fund; multi-timeframe analysis + strategy ensemble + crypto market-data access.

• dragon1086/prism-insight - Korean-market-focused multi-agent stock-analysis and trading system; built-in MCP integration.
• Tomortec/CryptoTradingAgents - Multi-agent LLM crypto-trading framework; applies the TradingAgents idea to crypto trading.
• EthanAlgoX/LLM-TradeBot - Multi-agent crypto-trading system; Binance real-time execution + adaptive strategy switching; combines ideas from TradingAgents and nof1.ai.
• huygiatrng/AlpacaTradingAgent - TradingAgents-style multi-agent framework connected to Alpaca for US-equity trading. (→ pairs with: [alpacahq/alpaca-mcp-server](#mcps-alpaca).)
• Yaolinwang/AITD - "AI Trading Agent for Everyone"; multi-agent project designed for retail users.
• flash131307/multi-agent-investment - Multi-agent equity-research system that lets LLM agents gather evidence, then uses a separate math layer to produce BUY / NEUTRAL / SELL.

• YichengYang-Ethan/oracle3 - Multi-venue (Kalshi / Polymarket / Solana) prediction-market autonomous agent; Wang-Transform pricing + Kelly criterion + cross-venue arbitrage.
• Ganador1/FenixAI_tradingBot - LangGraph + Ollama + CrewAI autonomous trading agent; local-LLM first.
• ryan-yuuu/crypto-trading-arena - Open-source crypto-trading arena; Claude / Claude Code agents compete head-to-head on live crypto data.
• FareedKhan-dev/multi-agent-trading-system - "Deep Thinking Trading System" tutorial implementation; beginner-friendly multi-agent example design.
• Tanglumy/Finance-Bro - Persona-styled finance "bro" trading-and-investment agent; uses the persona as the main interaction style.
• liangdabiao/autogen-financial-analysis - Microsoft AutoGen-based multi-agent financial-analysis system; VaR / Monte Carlo / factor models / visualization integration.

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

> Also see: [chrisworsey55/atlas-gic](#agents-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.

• chrisworsey55/atlas-gic - General Intelligence Capital's self-improving trading agent; focuses on continuous self-research rather than agent debate.
• Gajesh2007/ai-trading-agent - AI trading agent on Hyperliquid; single-LLM-driven execution; shows direct Hyperliquid integration.
• kweinmeister/agentic-trading - Trading-workflow example built on Google ADK + A2A interop; an alternative implementation outside LangGraph.
• danilobatson/ai-trading-agent-gemini - LunarCrush social-sentiment + Google Gemini crypto-trading agent; built with Next.js 15, Inngest, and Supabase.
• alsk1992/CloddsBot - Open-source AI trader across 1000+ markets, including Polymarket, Kalshi, Binance, Hyperliquid, Solana, and several EVM chains.
• hkirat/ai-trading-agent - "Trade using LLMs"; minimal TypeScript demo from Harkirat Singh; common on-ramp for TS learners.

Research / equity-research copilots

• ZhuLinsen/dailystock_analysis - Daily LLM-driven stock-screening dashboard; multi-channel push (WeChat / Feishu / Telegram / Discord / Slack / email); 11 built-in strategies + agent stock-Q&A; deploy-by-GitHub-Actions.
• AmadeusGB/alpha-arena - Live AI-agent competition and research platform; uses real-market conditions to improve agents.
• TNT-Likely/PanWatch - PanWatch / "盯盘侠"; AI-driven stock-monitoring assistant; multi-account positions + agent analysis + PWA mobile.
• YoungCan-Wang/WyckoffTradingAgent - AI stock-analysis assistant for A/HK/US equities; uses Wyckoff price-volume logic and ships CLI, web, and MCP tools.
• HKUSTDial/DeepEar - DeepEar / "顺风耳"; HKUSTDial's open-source deep-research and signal-tracking framework; joint multimodal news + price tracking.
• kamathhrishi/finance-agent - Earnings-call / SEC-filing / news Q&A agent; clean RAG-over-disclosures implementation.

> Also relevant: [ginlix-ai/LangAlpha](#agents-langalpha) and [oficcejo/aiagents-stock](#agents-tradingagents) both include research-copilot screens, but their main entries stay with the multi-agent systems they belong to.

Real-money / competition experiments

• LuckyOne7777/LLM-Trading-Lab - Real-money six-month experiment; ChatGPT manages a real US-equity micro-cap portfolio under strict pre-defined rules; ships with a 40-page evaluation paper.
• 195440/nof1.ai - Open-source autonomous AI trading agent from the nof1 family; TypeScript port.
• oficcejo/alpha-arena-okx - OKX re-implementation of nof1.ai's Alpha Arena; DeepSeek / Qwen3-Max as decision-makers; useful when comparing Chinese-language nof1 projects.
• wquguru/nof0 - nof1.ai Alpha Arena reimplementation with Go backend, Next.js UI, Hyperliquid, LLM executors, backtests, leaderboards.

Prediction-market specialists

• ryanfrigo/kalshi-ai-trading-bot - Grok-4-driven Kalshi prediction-market multi-agent trading system; portfolio optimization + 5-gate risk engine.
• OctagonAI/kalshi-trading-bot-cli - AI-native CLI for Kalshi and Polymarket; researches an event, estimates probability, then compares it with the live order book.
• jvnhaoWen/PolyAgent - Polymarket-focused multi-skill trading agent; focused single-venue Polymarket LLM agent.

> Also useful here: [agent-next/polymarket-paper-trader](#mcps-polymarket-paper-trader) is listed under MCPs because it is a paper-trading simulator, but it is built for AI agents.

> Also see: [YichengYang-Ethan/oracle3](#agents-oracle3) is listed with multi-agent systems above, and it is especially relevant here for multi-venue prediction-market arbitrage.

Benchmarks & evaluations

• ulab-uiuc/live-trade-bench - Live-market evaluation for trading agents; UIUC ULab's live-eval benchmark; distinct from backtest-only benchmarks.
• Open-Finance-Lab/AgenticTrading - Open-Finance-Lab's academic framework + dataset for agent-trading research.
• vals-ai/finance-agent - Finance-agent benchmark / task suite from vals-ai.

• HKUSTDial/DeepFund - Multi-agent fund-investment benchmark; LLM analysts evaluate stocks in a unified trading arena with leaderboard.

Strategy coding / self-improving agents

• paperswithbacktest/pwb-alphaevolve - DeepMind AlphaEvolve-style agent that uses an LLM to write and improve trading strategies for backtesting.
• Miasyster/QuantGPT - Agent-driven A-share factor research engine; 8 MCP tools span hypothesis → backtest → score → WQ BRAIN submission. (Distinct from rnikitin/QuantGPT.)

> Note: TauricResearch/Trading-R1 is not listed yet because its terminal has not launched. It can be added once the project is publicly usable.

MCPs

MCPs are servers that let an agent call external tools through the Model Context Protocol. In this list, they mostly cover market data, broker or exchange actions, research tools, and backtesting services.

> [!NOTE] > Same author to compare: guangxiangdebizi/ maintains [FinanceMCP](#mcps-financemcp) for data access and [TradingAgents-MCPmode](#mcps-tradingagents-mcpmode) for TradingAgents-style research tools. They solve different problems, so they stay in separate sections.

Market data / data providers

-

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: LLMQuant
• Source: LLMQuant/awesome-trading-agents
• License: CC0-1.0

Install and usage instructions live in the source repository linked above.