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 › Investment & VC › Kalshi Trading Bot CLI
✦ Free & open sourceInvestment & VC

Kalshi Trading Bot CLI

AI-native CLI for trading Kalshi prediction markets with deep research and a 5-gate risk engine.

AI-native CLI for Kalshi Prediction Markets

Run fundamental research, calculate model edge, and execute trades with half-Kelly sizing.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
6.9
ZEKAI
Powerful CLI for Kalshi quants.
Free & open source · Investment & VC
Ease of setup4
Usefulness9
Maintenance9.5
Community5
★ 393
GITHUB
Oct 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

kalshi-trading-bot-cli is an AI-native command-line interface designed to find edge and execute trades on Kalshi prediction markets. It is built for algorithmic traders and quantitative professionals who want automated probability estimates and systematic execution.

Runs on
Cross-platform
Hosting
Desktop
Languages
TypeScript
License
MIT

What it is

The tool conducts deep fundamental research, generates independent probability estimates, and calculates edge by comparing model prices to live order books. Sigs are sized using half-Kelly and evaluated through a 5-gate risk engine before orders are placed.

Who it's for

It suits quantitative traders and developers familiar with the command line who trade prediction markets. It does not suit casual users looking for a graphical interface or non-technical traders without API access.

Key features

Deep Fundamental Research

Generates independent probability estimates, ranked price drivers, and catalyst calendars for every market.

5-Gate Risk Engine

Filters trade signals through Kelly, liquidity, correlation, concentration, and drawdown checks.

Octagon API Integration

Connects to external research APIs for AI-generated probability estimates and market-with-edge screens.

Basket Management

Builds diversified baskets, runs backtests, calculates correlation matrices, and validates portfolio parameters.

Reflection & Calibration

Turns settled positions into terse lessons and tracks Brier scores and category skill against the market.

How to start

Up and running in 3 steps

1
Install Bun version 1.1 or higher on your system
2
Run bunx kalshi-trading-bot-cli@latest to trigger the interactive setup wizard
3
Provide your Kalshi API credentials and LLM provider keys when prompted
Real talk

Our honest verdict

What's great

  • Calculates model edge against live order books automatically
  • Built-in 5-gate risk engine with half-Kelly sizing
  • Comprehensive portfolio tools including baskets, backtests, and correlation matrices
  • Includes paper trading ledger and settlement sync

Where it falls short

  • Requires Bun 1.1 or higher and will not run on Node.js
  • Requires active Kalshi API credentials with an RSA private key
  • Depends on external paid APIs like Octagon and Tavily for full AI research features
Cost

Pricing & license

Free under its open-source license, but requires paid API keys for Kalshi trading access and external AI research providers like Octagon and Tavily.

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

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: Kalshi Trading Bot CLI for Investment & VC
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 Kalshi Trading Bot CLI for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I run this using Node.js?

No, the bot explicitly requires Bun 1.1+ because it uses bun:sqlite and executes .tsx files directly.

Where are my configuration and database files stored?

All local configuration, caches, and the SQLite database are kept in the ~/.kalshi-bot/ directory.

How are trade sizes determined?

Signals are sized using fractional half-Kelly sizing and filtered through a 5-gate risk engine.

Radar

Latest AI news

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

See Zekai first in Google