AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Finance › finance-agent
✦ Free & open sourceFinance

finance-agent

An equity research agent that queries SEC filings directly via filesystem tools instead of vector databases.

Filesystem-native SEC research agent

Ditch the vector DB for a ReAct agent that reads 10-Ks, 10-Qs, and 8-Ks like a human analyst.

Free forever · open source · MIT
✓ Needs IT✓ Browser-based✓ Real-time collaboration
6
ZEKAI
A clever, minimalist approach.
Free & open source · Finance
Ease of setup4
Usefulness8
Maintenance7
Community5
★ 149
GITHUB
Jun 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

This tool is a research agent designed for finance professionals who need direct, verifiable answers from SEC filings. It replaces complex RAG pipelines with a simple filesystem-based approach, allowing the agent to browse, grep, and read documents directly.

Runs on
Web
Hosting
Self-host
Languages
Python
License
MIT

What it is

The agent uses a ReAct loop to perform filesystem operations like ls, read_file, and grep on a local corpus of markdown-converted SEC filings. By avoiding chunking and semantic search, it ensures that every cited figure is retrieved directly from the source document.

Who it's for

It suits quantitative researchers and analysts who prefer deterministic retrieval over probabilistic vector search. It is not for those who want a plug-and-play SaaS, as it requires managing a persistent filesystem and periodic SEC data ingestion.

Key features

Filesystem-native retrieval

Uses standard terminal tools like grep and ls instead of vector embeddings.

Automated SEC polling

Includes a background watcher that automatically fetches new filings from EDGAR.

Markdown-first corpus

Processes raw SEC HTML into clean markdown for reliable LLM parsing.

Optional web context

Integrates Tavily for real-time news to supplement historical filing data.

How to start

Up and running in 3 steps

1
Clone the repository and install dependencies including ripgrep.
2
Configure your environment variables with OpenAI and database credentials.
3
Run the bootstrap script to hydrate the corpus or initiate a batch ingest from EDGAR.
Real talk

Our honest verdict

What's great

  • Eliminates retrieval errors caused by chunking or semantic misinterpretation.
  • Provides direct, verifiable citations back to the source document.
  • Avoids the complexity of maintaining vector databases and embedding models.
  • Handles SEC-specific formatting quirks like table-cell collapsing automatically.

Where it falls short

  • Requires significant local storage for the full SEC corpus.
  • Needs technical configuration of Postgres, Redis, and filesystem volumes.
  • Ongoing costs for OpenAI API usage and potential cloud hosting fees.
  • Requires manual management of SEC EDGAR rate limits and data ingestion.
Cost

Pricing & license

The tool is free to use under its license. You are responsible for all infrastructure costs, including hosting, database storage, and API usage fees for the LLM and news search.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: finance-agent for Finance
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure finance-agent for you — and train your team.
Get it done for you ↗
Questions

FAQ

Why did you remove the vector database?

The developers found that modern LLMs are capable of navigating a filesystem and performing grep searches more accurately than traditional RAG pipelines.

Does it work for all public companies?

It currently includes a canonical list of 300+ US tech companies, but can be expanded if you manage the ingestion pipeline.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Finance — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google