relai-ai/relai-sdk
A platform for building reliable AI agents
Provides simulation environments for testing agents with synthetic data and mocked tools, LLM-based and code-based evaluators for benchmarking, and an optimizer (Maestro) that refines both prompt/configuration parameters and agent graph structure based on evaluation signals. Integrates with OpenAI Agents SDK, Google ADK, and LangGraph frameworks via a Python SDK with async support and platform-hosted evaluation and optimization services.
Stars
93
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/relai-ai/relai-sdk"
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.
imtt-dev/steer
The Active Reliability Layer for AI Agents. Catch failures, teach fixes, and automate reliability