Self-host TradingAgents
v0.7.1Multi-agent LLM research desk for market trading analysis
- Stars
- 121 372
What is TradingAgents?
TradingAgents is an Apache-2.0 framework from Tauric Research that imitates the structure of a trading desk. Four analyst roles (fundamentals, sentiment, news, technical) work concurrently, a bull camp and a bear camp argue over their reports, and then a trader, a risk group and a portfolio manager converge on a call for whichever symbol you name — any market Yahoo Finance lists, crypto pairs included. Language models come from your own accounts: numerous hosted APIs, Azure OpenAI and AWS Bedrock, or self-run inference via Ollama and OpenAI-style endpoints served by vLLM, LM Studio or llama.cpp; the fast tier and the heavy-reasoning tier may even sit on different providers. Operation is a terminal program (tradingagents) that can be driven non-interactively with per-run options and TRADINGAGENTS_* settings, or the Python API, and it can also be started from a locally built Compose image. Output goes to saved reports with an added one-page HTML version; every decision lands in a log that is later reconciled against actual returns and fed back into future runs, interrupted work can resume from checkpoints, and a backtest mode replays many symbols across many dates, scoring calls as excess return versus each market's index. Passing a holdings file lets the agents judge your real book. The project stresses it is a research tool: outcomes are non-deterministic and it is not trading advice.
TradingAgents alternatives
PanWatchOpen-source, self-hosted AI stock monitor for A-share, HK and US markets: portfolios, TradingAgents research, price alerts and paper trading.ComparePanWatch with TradingAgents
Vibe AStockSelf-hosted A-share trading workbench with real-time monitoring, sentiment analysis, AI reviews, trading journal, and multi-market research.CompareVibe AStock with TradingAgents
Superior Trade Trading TerminalAI-powered trading terminal for Hyperliquid where you sketch on charts and an agent creates validated Freqtrade strategies. Open-source under Apache-2.0.CompareSuperior Trade Trading Terminal with TradingAgents
Big-AGISelf-hosted, open-source AI workspace for experts: run 2 to 24 models in parallel with Beam, personas, image generation, voice and BYO API keys via Docker.CompareBig-AGI with TradingAgents
TITANSelf-hosted AI agent framework with specialist team, shared memory, earned autonomy. 36 LLM providers, 19 channels, web dashboard on port 48420. MIT licensed.CompareTITAN with TradingAgents
CasibaseOpen-source personal AI assistant with RAG knowledge bases, MCP tool use and autonomous agent loops; one self-hosted binary with 30+ model providers, SSO and audit logs.CompareCasibase with TradingAgents
HunterCode Community EditionSelf-hosted AI investment research for A-shares, HK & US stocks with local data storage and BYOK LLM support.CompareHunterCode Community Edition with TradingAgents
gpt-researcherSelf-hosted, open-source deep research agent: a planner splits your question, parallel researchers scan 20+ web or local sources, and it writes a cited report.Comparegpt-researcher with TradingAgents
Should you self-host TradingAgents?
TradingAgents scores 87/100 on selfhost.directory (how scoring works) and ranks #3 of 209 in AI Agents. It has 121 372 GitHub stars, +9 013 in the last 30 days.
It shipped 11 stable releases in the past year. The latest, v0.7.1, came out on 27 October 2026. New versions land roughly every 2 weeks.
Setup is moderate: expect some configuration beyond a single command. It is Apache-2.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is Orca (91/100, 119 211 stars). It scores higher overall, so compare the two before you pick. See TradingAgents vs Orca side by side.
Features
- Backtesting
- Checkpoint resume
- Command Line Interface
- HTML report export
- Local model support
- Multi-agent analysis pipeline
- Multi-market ticker support
- Multi-Provider LLM Support
- Parallel analyst execution
- Persistent decision memory log
- Point-in-time fundamentals
- Portfolio-aware runs
- Python API
- Structured agent debate
More in AI Agents
triggerOpen-source TypeScript platform for durable background jobs and AI agent workflows, self-hosted as a Docker Compose or Helm webapp plus worker stack.
TrinityTrinity is a self-hosted, open-source platform for running AI agents in production with human approval gates, git-native state, and audit trails.
UnderstudySelf-hosted, open-source AI agent that runs locally on your Mac: computer use, teach-by-demonstration skills, browser, shell, memory and 8 messaging channels.
UseAgentUseAgent is a self-hosted, open-source control plane for running multiple AI coding agents in isolated sandboxes with a shared event log.
ValmisSelf-hosted AI agent platform with secure credential proxying and 100+ integrations for team automation.
VicoaSelf-hosted, open-source AI orchestrator running 40+ coding agents in parallel across machines with web, mobile, and CLI access.
VisionClaw-Agent-Public-ReleaseSelf-hosted AI operations platform where specialist agents collaborate through hundreds of tools to deliver real business assets on your infrastructure.
WarrenWarren runs coding agents as isolated workloads on your infrastructure, managing workspace, lifecycle, spend limits, live events, and Git delivery.
webclawSelf-hosted web extraction turning pages into clean Markdown, JSON, and LLM-friendly text. CLI, HTTP API, and MCP server for AI assistants. Rust, AGPL-3.0.
web-uiOpen-source, self-hosted Gradio web UI for browser-use AI agents: automate websites with any major LLM, drive your own Chrome profile, and watch the browser over VNC.
WeKnoraTencent's open-source knowledge framework for teams: self-hosted RAG Q&A with citations, agents with sandboxed skills, and auto-generated wikis on swappable LLMs.
WorkWitRun your own AI assistant for office work — handles contract review and resume screening, with 40+ skills, MCP connectors, and team access control.
0 comments