Laminar
Rust-based observability platform for AI agents with tracing, evals, and SQL dashboards.
About
Rust powers the backend of Laminar, an open-source observability platform built specifically for AI agents rather than generic LLM apps. OpenTelemetry-native tracing captures execution automatically through one-line instrumentation of the Vercel AI SDK, Browser Use, Stagehand, LangChain, and direct OpenAI, Anthropic, and Gemini calls, with Python and TypeScript SDKs for custom spans. Its distinguishing move is treating traces as data: every trace is queryable with SQL from custom dashboards, the CLI, or an MCP server, so an agent can analyze its own telemetry, while natural-language signals watch for described behaviors and alert to Slack when they appear. An evals SDK with CLI runner and visualization UI plus annotation tools for building datasets close the improvement loop. Self-hosting is a docker-compose command away in lightweight or full configurations, and laminar.sh operates the managed cloud. The Apache-2.0 project from Y Combinator's summer 2024 batch has passed 3,000 GitHub stars and positions itself as the open alternative to closed agent monitoring suites.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Observability & Evaluation
- Price
- Freemium
- Platform
- Hybrid
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- Jul 29, 2026
Related Tools
UK AI Security Institute framework for large language model evaluations and benchmarks.
ML experiment tracking, visualization, and collaboration
Open source LLM engineering platform for tracing and analytics
Open-source library for evaluating and tracking LLM applications.
Open-source AI metadata tracker for logging and comparing ML experiments.
Python framework for unit testing and evaluating LLM applications with metrics like G-Eval.