● Covered by 1 source · 1 reportLow impact1 neutral
AI Agent Manages Kalshi Account with New Liquidity Incentive Program Toolkit
Key points
- Mirabilis AI agent manages a Kalshi account.
- Toolkit released for Kalshi's Liquidity Incentive Program (LIP).
- Toolkit includes an exact scoring model and public-API client.
- The agent incurred trading losses despite predictable payouts.
- The toolkit is MIT licensed and dependency-free.
AI Agent Manages Kalshi Account
Mirabilis, an autonomous AI agent developed using Claude Code, is operating a small live account on Kalshi, an event prediction market platform. The agent's net value, including losses, is publicly reported daily. This initiative serves as a case study for AI in financial markets.
New Toolkit for Kalshi's Liquidity Incentive Program
Mirabilis has released a toolkit called 'lip_ledger' for Kalshi's Liquidity Incentive Program (LIP). This toolkit provides an exact scoring model for LIP, a public-API client, and a command-line interface (CLI). It is designed for analysis, allowing users to calculate potential payouts and analyze order books without requiring an API key or placing orders.
Program Mechanics and Payout Model
The LIP scoring model evaluates each side of a market based on one-second snapshots. A reference price is determined by cumulative size, and qualifying bids are scored based on size and ticks below the reference. Payouts are calculated based on a pool, share, and counted fraction, paid daily if they exceed $1.00. The toolkit allows users to simulate these calculations.
Performance and Challenges
Over an eight-day period, the Mirabilis account received $20.30 in LIP rewards, while incurring $36.06 in trading losses. This indicates that while the LIP payouts are predictable, managing fill risk due to fast traders sweeping bids remains a significant challenge. The toolkit's documentation provides a post-mortem analysis of these challenges.
Toolkit Availability and Limitations
The 'lip_ledger' toolkit is open-source under an MIT license, dependency-free, and compatible with Python 3.9+. It reads only public endpoints. Users are cautioned that expected payouts assume consistent market conditions, and Kalshi may change its rules. The toolkit is not investment advice.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub cmc_internal/api GitHub github/collect GitHub mirabilis-agent/lip-ledger GitHub _private/browser GitHub get-started/accessibility GitHub open-source/sponsorsReporting from
An AI agent named Mirabilis, developed using Claude Code, is managing a small Kalshi account and has released a toolkit for Kalshi's Liquidity Incentive Program (LIP). The toolkit includes an exact scoring model and a public-API client, allowing users to analyze potential payouts and order book dynamics without placing trades.