#3535th of 42 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting
finrobot
Multi-agent equity research with code-computed valuations and LLM-written reports
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.3k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Last release
- Jul 2026
- Language
- Python
6,444 on 1 Apr 20268,263 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
FinRobot is a financial agent project in three generations: an AutoGen library (V0, educational), an OpenAI Agents SDK web app (V1), and a PydanticAI desktop, web and CLI system (V2). V2 runs a lead agent, five pipeline agents and three debate agents. DCF, DDM, LBO and comps figures come from pure-Python operators, and the LLM only writes the narrative.
Who it is for: Analysts and developers building equity research and valuation workflows
Strengths
- Valuation numbers come from 32 deterministic Python operators, not the LLM
- Seven data providers with failover, including SEC EDGAR, FMP, Finnhub and yfinance
- V2 runs as a desktop app, a local web UI or a CLI
- Ships 56 analyst playbooks and 7 research pipelines
Weaknesses
- Three separate codebases; pip install finrobot gives only the V0 educational package
- Desktop release is macOS Apple Silicon only and not notarized
- Local API in browser mode is unauthenticated
- Needs external API keys such as FMP and OpenAI; V3 is still in development
What it needs
- no GPU
- Docker
- Needs FMP API key, Finnhub, OpenAI API key, SEC EDGAR, Node.js, uv
- Models: OpenAI, Azure OpenAI
- port 5173
Also in Agent platforms
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 81 out of 100 |
| 2 | daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps | 81 out of 100 |
| 3 | resume-matcherTailors resumes and cover letters to job descriptions using local or hosted LLMs | 81 out of 100 |
| #4 | vibe-tradingFinance research agent for backtests, market data and broker connectors | 78 out of 100 |
| #5 | deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks | 77 out of 100 |