Langfuse is the open-source LLM engineering platform for tracing, prompt management, evaluation and datasets 111. Its official doors are the Langfuse observability plugin for Claude Code and Langfuse skills and tools, listed above 111. Alternatives that do the same job are MLflow Tracing 313, PostHog AI observability 414, and Pydantic Logfire 515.
- 1
Langfuselangfuse.comverified and signed
Open-source platform that traces, evaluates and improves AI agents, with a Claude Code observability plugin and skills/tools for tracing, prompt management, datasets and experiments 111.
+29 community tools built for it
for agents: langfuse-observability · langfuse · langfuse
- 2
- 3
- 4
Pydantic Logfirepydantic.devverified and signed
Observability platform for tracing production agents and turning failures into evaluation cases, with SQL queries over traces and logs 515.
+24 community tools built for it
for agents: Query telemetry data · Execute Python in a sandbox · Manage feature flags
Sources
- 1Langfuse: Open Source Agent Evals & Observabilitylangfuse.com · read 2026-10-29
- 3MLflow - Open Source AI Platform for Agents, LLMs & Modelsmlflow.org · read 2026-10-29
- 4PostHog – Your product’s context layerposthog.com · read 2026-10-29
- 5Pydantic | The end-to-end AI engineering stackpydantic.dev · read 2026-10-29
- 11langfuse-observability: declares "langfuse-observability" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13instrumenting-with-mlflow-tracing: declares "instrumenting-with-mlflow-tracing" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14instrument-llm-analytics: declares "instrument-llm-analytics" (the record we read and signed)unfragile.ai · read 2026-10-24
- 15Pydantic: declares "Query telemetry data" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
langfuse-observability · langfuse-observability verified and signed
Langfuse observability plugin for Claude Code — captures and exports traces, spans, and session telemetry from Claude Code to Langfuse for LLM monitoring, debugging, and evaluation
createChatPrompt · langfuse found in code, not yet checked
instrumenting-with-mlflow-tracing · instrumenting-with-mlflow-tracing verified and signed
Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent evaluation. Triggers on adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, tracing specific frameworks (LangGr
instrument-llm-analytics · instrument-llm-analytics verified and signed
Add PostHog AI Observability to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.
Query telemetry data · Pydantic verified and signed
Run SQL SELECT queries against a Logfire project's traces, logs, metrics, and exceptions for investigation and exploration. e.g. Find the 10 slowest LLM calls in the last hour e.g. Show me all exceptions in the checkout service today e.g. What is the p95 latency for the agent loop this week?
querying-mlflow-metrics · querying-mlflow-metrics verified and signed
Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics.
app-observability · app-observability verified and signed
Get RED metrics + service maps + frontend RUM + AI/LLM monitoring out of Grafana Cloud — Application Observability (`traces_spanmetrics_*` from OTel traces, p50/p95/p99 latency, exemplar-to-trace, traces-to-logs / profiles), Frontend Observability with the Faro Web SDK (Core Web Vitals, session repl
logfire-instrumentation · logfire-instrumentation verified and signed
Add Pydantic Logfire observability to application code — traces, logs, metrics, and AI/agent spans. Use when the user asks to add or configure Logfire, observability, tracing, logging, or monitoring; maximize useful telemetry; or understand what an app is doing. Supports Python, JavaScript/TypeScrip
· Comet website read, tools not yet checked
Comet is the creator of Opik, an end-to-end AI observability platform for developers with best-in-class agent testing, optimization, and monitoring.
· Pydantic Settings website read, tools not yet checked
Pydantic is the AI engineering stack for teams building with AI. Observe with Logfire, evaluate with Pydantic Evals, build type-safe agents with Pydantic AI, and track LLM costs with AI Gateway.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.