Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Run a multi-agent research debate on a stock ticker

Have TradingAgents' analyst, researcher, trader and risk roles analyse one ticker on one date and produce a reasoned report.

Try the promptRead the original (opens in a new tab)

The problem

How it works

TradingAgents models a trading firm with LLM agents: fundamentals, sentiment, news and technical analysts work in parallel, bullish and bearish researchers debate their findings, a trader drafts a decision and a risk team plus portfolio manager approve or reject it. You run it from the CLI with a ticker and date, through Docker, or from Python via `propagate`. Data comes from sources such as SEC EDGAR, Yahoo Finance, news and social feeds.

Results and limitations

The README presents the output as a debated trading decision for research, and states that results depend on many factors.

Before you try it

The maintainers say it is a research framework and not financial, investment or trading advice; Top 200 Repos does not offer investment advice either. It needs LLM and data API keys, which may cost money. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Python 3.11+ · Docker (optional)
Prerequisites
An LLM provider API key (or a local model) and data keys such as Alpha Vantage; FRED is optional.

Try it yourself: Research run for one ticker

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Set up TradingAgents to analyse [Ticker symbol] as of [Analysis date] using [Model provider]. Before running, list which API keys and data sources the run will call and estimate how many model calls it may make, then wait for my approval. Run it in research mode only: do not connect a brokerage or place any orders. Save the full analyst, debate and risk reports to [Report folder], then give me a plain-language summary of the bull case, the bear case and the main risks, with the data sources each claim came from. Label the outcome as a research artefact, not advice.

Treat the result as a learning and research exercise; never let the agent trade or move money.

Related videos

About TauricResearch/TradingAgents

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. TauricResearch/TradingAgents README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 9 Nov 2026, 22:22 UTC

    What this source supports
    • Analyst, researcher, trader, risk and portfolio manager agent roles
    • CLI with ticker and date flags, Docker and Python usage
    • Supports many LLM providers and local models via Ollama
    • Data from SEC EDGAR, Yahoo Finance, news and social sources
    • Disclaimer: research purposes only, not financial advice
Report a problem

Reported by source

Answer technical questions by letting async agents run experiments

Simon Willison sends research questions to cloud coding agents such as Claude Code for web and Codex Cloud, which write and run experiments in a dedicated repo and open a PR.

simonwillison.net · 6 Nov 2025anthropics/claude-code, openai/codex
Reported by source

Build a cited Q&A knowledge base over your own documents

Self-host RAGFlow, upload PDFs, Office files and scans, and ask questions that come back with traceable source chunks.

github.cominfiniflow/ragflow
Planned, not done

Hand off research and document tasks to the Dispatch agent in Claude Cowork

Anthropic’s Cowork docs describe Dispatch, a background agent in Claude Desktop that splits one request into child tasks, runs each as its own session and forwards permission prompts to you, even from your phone.

claude.com
Reported by source

Keep a resident desktop agent for research notes and blog work

Raj Chettri runs Nous Research's Hermes Agent on his desktop for scheduled research summaries, note filing, quick scripts and his blog's writing pipeline.

rajchettri-com.pages.dev · 25 May 2026NousResearch/hermes-agent
Reported by source

Let a coding agent run overnight ML training experiments

Point a coding agent at autoresearch so it edits a small GPT training script, runs short timed experiments and keeps what improves.

github.comkarpathy/autoresearch, anthropics/claude-code, openai/codex
Planned, not done

Run long research tasks with sub-agents in DeerFlow

DeerFlow 2.0 is an open-source agent harness from ByteDance that plans a task, hands parts to sub-agents and works in a sandbox with memory, skills and search tools, using any OpenAI-compatible model.

github.combytedance/deer-flow