Open Source Observability Alternatives to LangSmith

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Opik records what your AI app actually did. Every model call, agent step and tool call lands in a trace you can click through, and the same platform runs evals: test datasets, experiments, and AI-graded scores for things like hallucination.

Open source LLM engineering platform

Langfuse records what your LLM app actually does: every prompt, response, tool call, latency and token cost becomes a trace you can search, score and replay. Prompt versioning, datasets and evals (including LLM-as-judge) sit alongside it.

AI Observability & Evaluation

Phoenix is how you see why an LLM feature misbehaved. It traces every model call your app makes, captures the prompts and responses, and lets you score outputs with evals so you can tell whether last week's prompt change helped or hurt.

Latitude is the open-source ai monitoring platform.

Latitude watches your AI agents the way Datadog watches your servers. When you ship an app built on LLMs, you lose visibility the moment a prompt leaves your code, you can't see why an agent went off the rails or which step failed.