Your agents silently degrade in production. Kalibr keeps them on the optimal path — scoring every call, learning what works, routing automatically.

ThumbGate — 👍👎 Thumbs down a mistake. It never happens again. Pre-action gates for AI coding agents. SQLite+FTS5, Thompson Sampling, ContextFS. Works with Claude Code, Cursor, Codex, Gemini, Amp, OpenCode.

OpenClaw plugin for Kalibr autonomous routing. Captures LLM telemetry and agent outcomes via plugin hooks, reports to Kalibr for autonomous path optimization.

A discipline for governing autonomous AI agents in production.

Open infrastructure modules for reliable and governable agent systems.

GuardMesh — Portable policy checks for governed agent execution.

Failure-mode evaluation harness for agent systems.

Detect, score, and heal broken agent skills.

Production-tested patterns for running multiple AI agents. Framework-agnostic. From 9 agents in daily production.

Production-ready agent starter template with Kalibr routing wired in. Clone and ship.

Harness engine for AI Agents. From demo to production.

GitHub profile

Portfolio site — React + TypeScript + Vite.