kalibr-ai/kalibr-sdk-python
Your agents silently degrade in production. Kalibr keeps them on the optimal path — scoring every call, learning what works, routing automatically.
Kalibr is a Python SDK that uses Thompson Sampling to dynamically route requests across multiple LLM and tool paths, minimizing cost while optimizing for defined success criteria. It features auto-instrumentation for OpenAI, Anthropic, Google, and DeepSeek calls, and integrates with frameworks like LangChain, CrewAI, and OpenAI Agents SDK. The SDK supports multimodal routing for text, voice, and image tasks, and offers autonomous provisioning and coding agent setup capabilities.
Stars
24
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/kalibr-ai/kalibr-sdk-python"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
petterjuan/agentic-reliability-framework
ARF is an agentic reliability intelligence platform that separates decision intelligence (OSS)...
sarkar-ai-taken/riva
Local-first observability and control plane for AI agents.
Nubaeon/empirica
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG,...
soumendrak/ragwatch
An SDK for Python AI Agents. Under heavy development.
relai-ai/relai-sdk
A platform for building reliable AI agents