# TauricResearch/TradingAgents

> 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.

- Magnitude: 5.2 out of 10 — Peaking
- Stars: 117,967 total · +94 stars measured 2026-10-29, 00:02–04:17 UTC, ≈ 492 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2024-12-28 · Last push: 2026-10-27
- GitHub: https://github.com/TauricResearch/TradingAgents · Homepage: https://arxiv.org/pdf/2412.20138 · Page: https://gitnova.dev/en/r/TauricResearch/TradingAgents
- GitNova flagged it 11 hours before GitHub Trending.

## 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

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:02–04:17: 117873 → 117967 stars (+94). This is the change over that interval.
- Estimated end-of-day forecast: about +492 stars, using observed gains and the previous day.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #7, +654 stars.
- GitHub Trending this week: #5, +5,322 stars.
- About 79 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 22,566
- Issues and pull requests: 1,555
- Watchers: 874
- Average over the last week: 778 per day
- Usual pace: 196 per day
- Stars in the last hour (measured): 19
- Latest release: v0.7.1 (2026-10-27)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 119, 102, 119, 113, 156, 116, 128, 162, 156, 124, 122, 185, 197, 208, 174, 193, 154, 239, 192, 222, 251, 254, 500, 346, 341, 1192, 1647, 941, 486, 94

## Magnitude by day, last 14 days

09-26 3.7, 09-27 3.3, 10-18 3.7, 10-19 4.0, 10-20 4.0, 10-21 4.2, 10-22 4.8, 10-23 5.0, 10-24 4.6, 10-25 5.8, 10-26 8.2, 10-27 8.9, 10-28 7.5, 10-29 5.2

## Hacker News

- Multi-Agents LLM Financial Trading Framework — 120 points, 81 comments: https://news.ycombinator.com/item?id=49605822

## Spotted in now

- GitHub Trending Python today: #7, +654 stars
- GitHub Trending this week: #5, +5,322 stars

## Similar by description

1. **HKUDS/Vibe-Trading** — 3.2 · Steady · Finance & crypto · Python · +21 stars measured 2026-10-29, 00:04–04:19 UTC, ≈ 110 by evening
   AI agent for trading and quantitative research: runs backtests, factor analysis, paper trading and live strategies via LLM and MCP. Aimed at traders and quant developers.
   Full card: https://gitnova.dev/en/r/HKUDS/Vibe-Trading.md
2. **Diabloluo/deadlatch** — 0.0 · Quiet · Python · Not enough measurements today
   Local-first, advisory-only pre-trade risk gate for AI trading agents.
   Full card: https://gitnova.dev/en/r/Diabloluo/deadlatch.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 04:27 UTC, updated every 30 minutes.