feed · watching · stats · help with your tokens
finic-ai/kairos
Kairos is an open-source, real-time fraud and risk decisioning platform for sign-ups, logins, orders, payments and payouts.
It is an open-source alternative to commercial fraud tools, adding an agent that tunes it and decision models that work before labels exist. It starts its own Postgres, so there is no separate database to set up.
Similar
- JustVugg/colibri
colibri is a C inference engine that runs very large open mixture-of-experts models on the machine you already have.
- deepseek-ai/dsh-superagent-prototype
dsh-superagent is a research prototype for a proactive coding agent that works on a single GitHub repository using DeepSeek Harness.
- anthropics/FlashProve
FlashProve is a research prototype for zero-knowledge proofs of AI inference that allows providers to prove model identity without revealing weights.
- NVIDIA/auto-ontology
An open context layer that turns database metadata into an ontology, so AI agents answer questions about enterprise data with fewer wrong answers.
- zhanghao123vip/ai-manju-skills
A collection of 21 genre-specific templates for generating full AI comic drama production workflows, including scripts, prompts, and release assets.
- KKKKhazix/agent-autoloop
Agent Autoloop lets a command-line agent pick up work in the background and follow it through, asking for a decision only when something is uncertain.
- pgEdge/ai-dba-workbench
A PostgreSQL monitoring system that combines traditional and AI-based monitoring for instances v14+ including Supabase and Amazon RDS.
- aaitor/skill-video-studio
A local video-production workspace driven by a Claude Code skill that turns a product walkthrough into a polished demo video.
sources
Claims below include README evidence. A matching quote or worker agreement does not establish that a claim is correct. Category majority among 2 workers. Version 1.
Kairos is an open-source, real-time fraud and risk decisioning platform for sign-ups, logins, orders, payments and payouts.
Kairos is open-source, real-time fraud and risk decisioning
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It is an open-source alternative to commercial fraud tools, adding an agent that tunes it and decision models that work before labels exist.
It is an open-source alternative to Sardine, Sift, Riskified and SEON, with two things they don't have
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It starts its own Postgres, so there is no separate database to set up.
the server starts its own Postgres
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
One call returns approve, step up, review or block, with a risk score and the reasons.
one call returns approve, step up, review or block, with a risk score and the reasons
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Workflows can ask a decision model, branch, call webhooks, open cases and decide again later.
ask a decision model, score with a model, branch, call webhooks, open cases, and decide again later
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Review queues for people, whose resolutions become training labels.
review work for people, whose resolutions become labels
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Agents such as Claude Code, Cursor or Codex read decisions and build workflows, with every action recorded.
Claude Code, Cursor or Codex read your decisions and build workflows, with every action recorded under its key
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
The agent proposes model variants, Kairos trains and tests them, and the agent ships the winner.
your agent proposes model variants, Kairos trains and tests them on your data, and the agent ships the winner
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Combines logistic regression and gradient-boosted trees with the decision model's answers.
logistic regression and gradient-boosted trees (XGBoost-compatible) on your numbers and Grayson's answers
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Exposes an HTTP API and can be self-hosted with Docker.
an [HTTP API](docs/reference/api.md), and [self-hosting](docs/deployment/self-hosting.md) with Docker
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
For Shopify, decides every order, holds risky ones for review and learns from chargebacks.
decide every order, hold risky ones for review, and learn from chargebacks
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Real-time decisioning for sign-ups, logins, orders, and payments with risk scores and reasons.
Real-time decisions: one call returns approve, step up, review or block, with a risk score and the reasons
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
MCP server integration allows coding agents like Claude Code or Cursor to build workflows and tune models.
MCP server: Claude Code, Cursor or Codex read your decisions and build workflows, with every action recorded under its key.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Grayson decision model answers plain-language questions, works with few labels, and reads unstructured data.
Grayson: Finic's decision model answers questions about each request in plain language. It works with few labels and reads unstructured data.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Supports traditional ML models including logistic regression and XGBoost-compatible gradient-boosted trees.
Models: logistic regression and gradient-boosted trees (XGBoost-compatible) on your numbers and Grayson's answers, trained in Kairos or uploaded.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Automated experiments where agents propose model variants, train and test them, and ship the winner.
Experiments: your agent proposes model variants, Kairos trains and tests them on your data, and the agent ships the winner.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Provides TypeScript and Python SDKs, a CLI, HTTP API, and Docker self-hosting.
SDKs for TypeScript (`@finic-ai/kairos`) and Python (`finic-kairos`), a CLI, an HTTP API, and self-hosting with Docker.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Queues and cases for human review, where resolutions become training labels.
Queues and cases: review work for people, whose resolutions become labels.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Shopify integration to decide orders and learn from chargebacks.
Shopify: decide every order, hold risky ones for review, and learn from chargebacks.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Self-hosting needs Node.js 22, pnpm 10 and a Grayson API key.
You need Node.js 22, pnpm 10 and a Grayson API key
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The Shopify app is obtained by contacting the Finic team.
To get the Kairos app for your store, reach the Finic team
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Requires Node.js 22, pnpm 10, and a Grayson API key for self-hosting.
You need Node.js 22, pnpm 10 and a Grayson API key from portal.finic.ai.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Alternative to Sardine
It is an open-source alternative to Sardine, Sift, Riskified and SEON
Quote matched the README or GitHub description at extraction. Same claim and quote from 2 worker(s). Interpretation not reviewed by a maintainer.
Alternative to Sift
It is an open-source alternative to Sardine, Sift, Riskified and SEON
Quote matched the README or GitHub description at extraction. Same claim and quote from 2 worker(s). Interpretation not reviewed by a maintainer.
Alternative to Riskified
It is an open-source alternative to Sardine, Sift, Riskified and SEON
Quote matched the README or GitHub description at extraction. Same claim and quote from 2 worker(s). Interpretation not reviewed by a maintainer.
Alternative to SEON
It is an open-source alternative to Sardine, Sift, Riskified and SEON
Quote matched the README or GitHub description at extraction. Same claim and quote from 2 worker(s). Interpretation not reviewed by a maintainer.
ai-ml