#87 · Primary category： MLOps & Evaluation
lmnr
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
Project last updated：08/29/26
GitHub Stars
3.2K
Forks
228
Contributors
29
License
Apache-2.0
Why we included this project
When a production agent misbehaves, scattered logs rarely tell you why. Laminar records each run as a structured trace, capturing every LLM call and tool invocation, so you can replay it and pinpoint where the agent went wrong. You can also describe the failure mode you care about in plain English, such as "agent is stuck in a loop," and get a Slack ping the next time it shows up. The eval SDK and CLI turn captured failures into datasets you can test against in CI, and the Rust-based core keeps ingestion and storage cheap even at high volume. If you run agents built with LangChain or the Vercel AI SDK and want one self-hosted place to debug and evaluate them, this is a solid fit.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
netron
Visualizer for neural network, deep learning and machine learning models