Skip to main content
View on GitHub → Find arbitrage opportunities across prediction markets. One AISA_API_KEY matches equivalent events on Polymarket and Kalshi, compares implied probabilities, and verifies orderbook depth so agents can execute with confidence.

​
Install

First, install the AIsa CLI if you have not already: 
npm install -g @aisa-one/cli
Then install the skill: 
aisa skills install prediction-market-arbitrage

​
What can agents do with it?

Cross-exchange scan

“Find NFL games with priced markets on both Polymarket and Kalshi.”

Spread detection

“Flag outcome pairs where combined implied probability < 1.0.”

Liquidity verification

“Check top-of-book depth on both sides before triggering an alert.”

Sports arb workflow

“Daily NBA/NFL/MLB arbitrage scan with configurable edge threshold.”

Elections & macro

“Surface arbitrage windows on election, rate, and macro event markets.”

Execution prep

“Produce a trade plan with size limits from orderbook depth.”

​
How it works

1

Match equivalent events

Use the /matching-markets/sports (and /sports/{sport}) endpoints, or slug/ticker heuristics, to pair up a Polymarket token_id with a Kalshi market_ticker for the same real-world event.
2

Compare prices

Call each platform’s market-price endpoint. An arbitrage window exists when the combined implied probabilities of mutually-exclusive outcomes sum to less than 1.0.Example: buying complementary outcomes at 0.40 and 0.55 totals 0.95 — a 0.05 edge before fees.
3

Verify liquidity

Before executing, pull each platform’s orderbook to confirm there’s enough depth at the quoted price to absorb your size.
When passing a path parameter with curl, make sure every {placeholder} is replaced with a concrete value. Literal { and } trigger cURL’s URL globbing syntax and will fail.

​
Quick start

export AISA_API_KEY="your-key"

​
1. Match markets

# Find NBA games with markets on both platforms for a specific date
curl "https://api.aisa.one/apis/v1/matching-markets/sports/nba?date=2025-08-16" \
  -H "Authorization: Bearer $AISA_API_KEY"

​
2. Compare prices

# Polymarket implied probability
curl "https://api.aisa.one/apis/v1/polymarket/market-price/POLY_TOKEN_ID" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Kalshi implied probability
curl "https://api.aisa.one/apis/v1/kalshi/market-price/KALSHI_MARKET_TICKER" \
  -H "Authorization: Bearer $AISA_API_KEY"

​
3. Check orderbook depth

# Polymarket orderbook
curl "https://api.aisa.one/apis/v1/polymarket/orderbooks?token_id=POLY_TOKEN_ID" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Kalshi orderbook
curl "https://api.aisa.one/apis/v1/kalshi/orderbooks?ticker=KALSHI_MARKET_TICKER" \
  -H "Authorization: Bearer $AISA_API_KEY"

​
Python client

# Full sports arbitrage scan for a given day
python3 scripts/arbitrage_finder.py find-sports-arbitrage --sport nba --date 2025-08-16

# Check liquidity across a matched pair
python3 scripts/arbitrage_finder.py check-liquidity \
  --polymarket-token-id POLY_TOKEN_ID \
  --kalshi-ticker KALSHI_MARKET_TICKER

# Compare prices only (no liquidity check)
python3 scripts/arbitrage_finder.py compare-prices \
  --polymarket-token-id POLY_TOKEN_ID \
  --kalshi-ticker KALSHI_MARKET_TICKER

​
Endpoint reference

EndpointMethodPurpose
/matching-markets/sportsGETAll sports
/matching-markets/sports/{sport}GETBy sport
/polymarket/market-price/{token_id}GETPolymarket price
/kalshi/market-price/{ticker}GETKalshi price
/polymarket/orderbooksGETPolymarket orderbook
/kalshi/orderbooksGETKalshi orderbook

​
Get started

  1. Sign up at aisa.one (new accounts start with $2 free credit).
  2. Generate an API key from the console.
  3. export AISA_API_KEY="your-key" and install the skill: 
    npm install -g @aisa-one/cli
aisa skills install prediction-market-arbitrage

Prediction Market API

All Polymarket, Kalshi, and matching-markets endpoints.

Market Data skill

The underlying data skill this one builds on.

Rate Limits

Concurrency caps when running arb scans.