GoKawiilFinic launches Kairos, an open-source fraud and risk decisioning platform
Finic has released Kairos, an open-source real-time fraud and risk decisioning system that evaluates sign-ups, logins, orders, payments and payouts, returning an approve, step up, review or block decision along with a risk score and supporting signals. The platform includes an MCP server so AI coding agents like Claude Code, Cursor or Codex can build workflows, propose model variants and tune detection models, alongside traditional machine learning options like logistic regression and gradient-boosted trees, with SDKs for TypeScript and Python plus self-hosting via Docker.
GoKawiil's interpretation of the reporting above, not reported fact.
Kairos positions itself as a free alternative to commercial fraud-detection vendors such as Sardine, Sift, Riskified and SEON, which could lower the barrier for smaller companies to adopt real-time risk decisioning. Its emphasis on AI agents tuning models and its 'Grayson' decision model working with few labels suggests an attempt to address the common problem of fraud teams lacking enough confirmed fraud cases to train traditional ML systems, though how well this performs at scale remains to be seen.
- Kairos is an open-source real-time fraud and risk decisioning platform from Finic.
- It integrates with AI coding agents via MCP to let them build workflows and tune detection models directly.
- It combines a custom decision model (Grayson) with traditional ML like logistic regression and XGBoost-compatible trees, offered via SDKs and self-hosting.
Source: github.com, 2026-11-03
Published there as: “Show HN: Kairos – Open-source risk and fraud decisioning platform”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.