Rezzecup / polymarket-kalshi-arbitrage-bot
What it does
Sentence-transformer semantic matching to find equivalent markets across platforms. Jaccard similarity + date/entity hints + optional LLM verification (12 parallel workers via Chutes.ai). PM2 process management; FastAPI + SSE for live updates.
What we learned from it
semantic matching for cross-platform market identification is the under-appreciated half of arbitrage. Most arb bots match on string equality and miss obvious pairs. The semantic approach generalizes much better.
Find the author
- Repository: github.com/Rezzecup/polymarket-kalshi-arbitrage-bot
- GitHub profile: @Rezzecup
- Twitter/X: @chain_sats
Watch a Kalshi bot get built live.
Join the free monthly group webinar on August 25 at 6:00 PM Pacific. See the product, bring a question, and get the calendar invite by email.
We'll email the calendar invite and reminders for this webinar. Registering does not create an account. See our Privacy Policy.
Don't want to maintain your own bot?
Bot for Kalshi is the no-code platform for automated prediction-market trading — visual builder, signals, encrypted credentials, kill switch. The infrastructure these open-source projects build, ready to use.
One plan includes the visual builder, paper and live modes, hosted execution, and risk controls. Cancel anytime.