An open platform that shows every model call: traces, cost, quality scores and prompt versions. Use it in the cloud or self-host it.
All repositories
Evals & observabilitypydantic
logfire
An observability platform from the makers of Pydantic: it traces plain code, model calls and agents. Built on OpenTelemetry, with an open-source SDK.
Who it is for
For Python developers who want app and LLM traces in one tool.
How to start
- Install:
pip install logfire. - Authenticate:
logfire auth. - Add instrumentation following the README example and look at your first trace.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+53Sep 6 — Oct 3
Author's description
AI observability platform for production LLM and agent systems.
More in «Evals & observability»
A long-standing ML platform that now covers LLM apps too: tracing, evaluation, a prompt registry and a model gateway. Plugs into most frameworks.
A command-line tool for testing prompts and agents: describe cases in a config and compare models. Also does red teaming and vulnerability scanning. Plugs into CI.
A platform for debugging and evaluating LLM apps: traces, automated quality checks and dashboards. Supports RAG and agent chains, and can be self-hosted.
OpenAI's framework for evaluating models plus a registry of ready-made benchmarks. A historically important project that shows how eval templates are structured.
A pytest-style framework for testing LLM apps: ready-made metrics for RAG, agents and chatbots, plus trace-based checks. Results can be pushed to a cloud.