TauricResearch/TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework
About the project
A framework that simulates a trading firm with LLM agents (analysts, researchers, trader, risk manager) debating markets and producing trading decisions. Built for research, not real trading.
Useful for
- Run a trading simulation for a ticker and watch the agents debate a trade
- Plug in a preferred LLM provider (OpenAI, Gemini, Claude, DeepSeek, Ollama) and compare decisions
- Study how data and news affect the agents' trading decisions
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 527 stars today. The usual pace is 196 per day, so that's 2.7× as much.
- Hacker News: “Multi-Agents LLM Financial Trading Framework” — 120 points, 5 days ago.
- About 185 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 105,362
- Stars in a day
- 533
- Forks
- 20,208
- Issues and pull requests
- 1,299
- Watchers
- 801
- Language
- Python
- License
- Apache-2.0
- Latest release
- v0.4.0 · August 31, 2026
- Created
- December 28, 2024
- Last push
- September 7, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Multi-Agents LLM Financial Trading Framework120 points, September 8, 2026
Spotted in
- September 13, 2026Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/TauricResearch/TradingAgents)Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.