AI-oriented quantitative investment platform from Microsoft covering data, model training, backtesting and order execution for quant research.
AI4Finance-Foundation/FinRobot
An open-source agentic AI framework for financial research, combining LLMs with deterministic valuation tools and multi-agent workflows.
Open-source alternative to:Bloomberg Terminal
- Stars
- 8,384
- Forks
- 1,416
- Open issues
- 81
- Last commit
- 14 days ago
Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.
What is it?
FinRobot is an open-source agent framework for financial decision support, covering equity research, quantitative trading, risk analysis, investment banking, private equity and wealth management. Its design separates duties: language models handle reasoning, narration and report writing, while all financial figures such as DCF, DDM, LBO, WACC, comparable-company analysis and Monte Carlo simulation are produced by pure-Python code with provenance tracking.
The repository holds three generations. finrobot_desktop (V2) is the current production system, a desktop research workstation built on PydanticAI, FastAPI and React/Tauri, with a Lead Agent coordinating data, analysis, modeling, synthesis and report agents plus bull, bear and judge debate agents. finrobot_equity (V1) is a self-hosted web app that turns a ticker into an HTML or PDF equity report. finrobot_autogen (V0) is the original AutoGen-based library behind the research paper, with tutorial notebooks, and is intended for learning rather than production.
The V2 desktop app is available for macOS Apple Silicon, and a local web UI and CLI run the same engine on other platforms. The project is licensed under Apache-2.0.
Key features
- 01Deterministic valuation operators (DCF, DDM, LBO, comps, Monte Carlo) keep financial numbers out of LLM output.
- 02Multi-agent pipeline with a lead orchestrator, role-based research agents and bull/bear/judge debate agents.
- 03Seven research pipelines covering company research, DCF, comps, LBO, DDM, earnings and IC memos.
- 04Data providers with failover, including FMP, Finnhub, yfinance and SEC EDGAR.
- 05Desktop app, local web UI and a CLI (for example `finrobot research AAPL`) share one engine.
- 06Tutorial notebooks for annual report generation, forecasting and multimodal chart analysis in the V0 library.
Use cases
- Producing structured equity research reports with valuation and risk sections for a given ticker.
- Teaching or prototyping how financial AI agents are wired together using the V0 AutoGen library.
- Running a self-hosted web service that generates shareable equity research reports.
- Building investment committee style memos that combine bull and bear arguments.
In collections
Topics
FAQ
- What is FinRobot?
- An open-source agentic AI framework for financial research, combining LLMs with deterministic valuation tools and multi-agent workflows. FinRobot is an open-source agent framework for financial decision support, covering equity research, quantitative trading, risk analysis, investment banking, private equity and wealth management. Its design separates duties: language models handle reasoning, narration and report writing, while all financial figures such as DCF, DDM, LBO, WACC, comparable-company analysis and Monte Carlo simulation are produced by pure-Python code with provenance tracking.
- Is FinRobot free to use? What license does it have?
- FinRobot is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is FinRobot still maintained?
- Actively maintained. The last commit to FinRobot was on Oct 24, 2026.
- What can I use FinRobot for?
- Producing structured equity research reports with valuation and risk sections for a given ticker. Teaching or prototyping how financial AI agents are wired together using the V0 AutoGen library. Running a self-hosted web service that generates shareable equity research reports. Building investment committee style memos that combine bull and bear arguments.
- Where can I get FinRobot?
- The source code and installation instructions are on GitHub: https://github.com/AI4Finance-Foundation/FinRobot
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source large language models fine-tuned for financial tasks such as sentiment analysis, forecasting and financial NLP benchmarks.
An Obsidian plugin that brings AI agents such as opencode, Claude Code and Codex into your vault for research, writing and note work.
An open-source personal trading agent that runs research, backtests, paper trading and broker connections from one command, via CLI, Web UI, API or MCP.
A-share-specialized multi-agent LLM investment research framework, forked from TradingAgents, with seven analyst roles and bull/bear debate.
Open-source Python data platform that connects financial and other data sources and exposes them to Python, Excel, AI agents and REST APIs.