Tracing, logging, and monitoring for LLM and agent systems. Ranked by community traction, with live GitHub stars and what each is best at.
Short answer: the best observability for AI agents by community traction is Langfuse (★ 33k), followed by Phoenix and Helicone.
✓ Live data verified
Open-source LLM engineering platform — tracing, evals, prompt management, and metrics for agent apps. Best for LLM tracing.
Arize's open-source observability for LLM apps — OpenTelemetry-based tracing and evaluation. Best for OTel tracing.
Open-source observability for LLM apps via a proxy — logging, caching, and cost tracking with one header. Best for cost tracking.
By community traction, Langfuse (★ 33k) leads the observability in our directory. Open-source LLM engineering platform — tracing, evals, prompt management, and metrics for agent apps.
Langfuse is the most-starred open-source option; Phoenix and Helicone are strong runners-up.
Langfuse, at ★ 33k (live count).
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.