Thesis-driven
Every position starts as a written hypothesis with valuation, time horizon, and dimension expectations. Research is evaluated against the thesis, not in the abstract.
Cents
Thesis-driven investment research, agent-orchestrated.
Cents is a CLI for the AI/finance crowd that treats investing as a hypothesis-testing exercise. Write down a thesis, let seven specialised research agents gather evidence, and track outcomes against the original hypothesis — so you measure thesis accuracy, not just P&L.
git clone https://github.com/wolfbane/cents.gitcd cents && pip install .Demo recording coming soon.
The asciinema cast at /demo.cast is a placeholder. Once recorded,
it will play here in-browser.
Multi-agent
Seven specialised agents — fundamentals, technical, macro, sentiment, moat, insider, plus an orchestrator — pull from FMP, Alpaca, FRED, and NewsAPI, each contributing evidence and a conviction delta.
Accuracy-tracking
Outcomes are recorded against the thesis that opened the position, so you can answer “how often is my thinking right?” — not just “did it go up?”
Get started
Section titled “Get started”Quickstart
A 5-step walkthrough from zero to your first scan. Read the quickstart →
Star on GitHub
Source, issues, and discussions live at github.com/wolfbane/cents.
Not financial advice. Cents is an educational and research
tool for tracking your own investment theses. Outputs are model-generated and
may be inaccurate. You are solely responsible for your own investment
decisions.