ai4finance-foundation / finrobot Architecture and code health
FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models
Claude Code, Cursor, Codex or VS Code. No key. You approve one sign-in in your browser.
Releases on GitHub (latest desktop-v0.1.0, Jul 7, 2026)
Repowise maps public repos from their source. Not affiliated with ai4finance-foundation. What is Repowise?
What is finrobot?
FinRobot is an open-source agentic AI framework for financial decision intelligence, built for equity research, quantitative trading, risk analysis and similar financial work. Its core idea is that models reason, software computes, agents orchestrate and systems verify: financial figures come from deterministic Python code, while language models handle reasoning and report writing. The project is written mainly in Python, and its desktop app adds TypeScript and Rust components.
Written by a model from the README and the source, like the other summaries and answers on this page
928 files and 9,982 symbols in 4 modules, led by Python (562 files) and TypeScript (255).
Explore finrobot
- DocumentationModule-by-module documentation, 1,202 pages.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score and the findings behind it.
- CommitsEach commit's effect on code health.
- OverviewEverything else the index found: contributors, decisions, what changed this week.
Ask about this code in your agent
This connects Repowise to finrobot's code. It does not install finrobot.
Useful if you want to change or fork finrobot: your agent can ask how it is put together and get answers that cite its files.
Ask about finrobot
Answers come from finrobot's README and source, with the files they cite. Two free answers a day without an account.
Want this for your own codebase? Map your repo free
About this page
Get a page like this for your own codebase
Repowise built this map of ai4finance-foundation/finrobot from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.
Free for 2 public repos, with a page like this one. No card. See how Repowise works
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub
ai4finance-foundation/finrobot FAQ
What is FinRobot?
FinRobot is an open-source agentic AI framework for financial decision intelligence. It combines foundation models with financial tools, quantitative models and multi-agent workflows for equity research and risk analysis.
How does FinRobot work?
FinRobot runs multi-agent workflows in which a Lead Agent passes work through data, analysis, modeling, synthesis and report agents. Valuation figures such as DCF, DDM, LBO and WACC are computed by deterministic Python code, and the LLM writes the narrative around them.
What language is FinRobot written in?
FinRobot is written mainly in Python. Its desktop app also includes TypeScript for the frontend and Rust for the Tauri shell.
How is the FinRobot code organized?
The code is split into three directories: finrobot_desktop for the V2 production desktop app, finrobot_equity for the V1 web app, and finrobot_autogen for the original V0 AutoGen library.
Who is FinRobot for?
FinRobot is for building decision-grade financial applications in equity research, quantitative trading, risk analysis, investment banking, private equity and wealth management.
What license does FinRobot use?
FinRobot uses the Apache-2.0 license, so the project is open source under that license.
Code health
On the leaderboards:#9 of 71 Python repos
Key features of finrobot
- Keeps financial numbers in deterministic pure-Python operators, separate from LLM-written narration, with provenance tracking on outputs.
- Coordinates data, analysis, modeling, synthesis and report agents through a Lead Agent in one pipeline.
- Runs bull, bear and judge debate agents to test an investment thesis before it reaches the final report.
- Provides research pipelines for company research, DCF, comps, LBO, DDM, earnings and investment committee memos.
- Pulls market data and company filings through providers with failover, including FMP, Finnhub, yfinance and SEC EDGAR.
How ai4finance-foundation/finrobot works
FinRobot is made of three projects that share one financial domain layer, each in its own directory. finrobot_desktop/ is the V2 production system, a native desktop research app built on PydanticAI, FastAPI and React/Tauri, where a Lead Agent passes work to data, analysis, modeling, synthesis and report agents. Bull, bear and judge debate agents test the investment thesis, and the result is a traceable research report. Valuation calculations such as DCF, DDM, LBO and WACC run as deterministic operators, so the LLM narrates numbers that code has already computed. finrobot_equity/ is the V1 self-hosted web app, with a FastAPI interface that turns a ticker into a shareable HTML or PDF report. finrobot_autogen/ holds the V0 original AutoGen library, and the pip-installed finrobot package is built from it under the same import name.
The codebase has 928 files and 9,982 symbols in 4 modules, led by Python, TypeScript and JavaScript. Code health is 8.3 out of 10, rated good.
Maintain ai4finance-foundation/finrobot?
Claim this page, add a badge to the README, or re-index it.
Claim this page
Sign in with GitHub and we check that you are an admin or maintainer of ai4finance-foundation/finrobot. Then add a badge to the README that links readers here.
Add a badge to your README
Readers click through to this page and can ask finrobot's code a question. A badge also re-indexes the repo every week and marks you as the verified maintainer.
[](https://repowise.dev/repo/ai4finance-foundation/finrobot?src=badge_ask)Paste it at the top of README.md, under the title.
Added it already? Verify to get the mark now instead of tomorrow.
Need HTML or the larger health card? More formatsHide more formats
This badge as HTML
<a href="https://repowise.dev/repo/ai4finance-foundation/finrobot?src=badge_ask"><img src="https://api.repowise.dev/badge/wiki/ai4finance-foundation/finrobot.svg?label=ask" alt="repowise: Ask this codebase"></a>Code health card
The score, its change since the last index, and when it was measured. Follows the reader's light or dark theme.
<a href="https://repowise.dev/repo/ai4finance-foundation/finrobot?src=badge_card"><picture><source media="(prefers-color-scheme: light)" srcset="https://api.repowise.dev/badge/health/ai4finance-foundation/finrobot.svg?style=card&theme=light"><img src="https://api.repowise.dev/badge/health/ai4finance-foundation/finrobot.svg?style=card" alt="repowise code health" width="500" height="168"></picture></a>