AI Tool

Langfuse

Evals Observability

An open-source LLM engineering platform for tracing what an application's prompts and agent steps actually did in production, plus tools for prompt management and running evaluations against test datasets.

Pricing: Open-source

Visit Langfuse →

Related tools

Arize AIAn ML and LLM observability platform that monitors models and AI applications in…BraintrustAn evaluation platform for AI applications: run a prompt or pipeline change against a…CometAn ML experiment-tracking platform (logging training runs, metrics and models) that has…GalileoAn evaluation and observability platform for LLM applications that scores production and…Patronus AIAn AI evaluation and safety platform that automatically scores an LLM's outputs against…Weights & BiasesA long-standing ML experiment-tracking platform - logging runs, metrics and model…
271 hosted MCP tools run here with no signup: /mcp/tools/