Langfuse

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

[Beta] Community-maintained Terraform Provider for Langfuse

🪢 Langfuse Python SDK (v4, OpenTelemetry). Tracing: get_client() / start_as_current_observation — not the legacy Langfuse().trace() client.

🪢 An opencode plugin that instruments sessions in Langfuse

🪢 Langfuse JS/TS SDKs - Instrument your LLM app and get detailed tracing/observability. Works with any LLM or framework

Trace Pi coding agent sessions with Langfuse — agent turns, model generations, token usage with cache and reasoning splits, cost, tool calls, and nested subagents.

Run your Langfuse experiment with your GitHub action workflow.

Trace OpenAI Codex CLI coding sessions, agent turns, tool calls, token usage, and subagents with Langfuse for comprehensive observability.

Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation