Vibe Coding Discoverlangfuse
View on GitHub🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Open source LLM engineering platform for tracing, evaluating, prompt management and debugging of LLM and agent applications. Self-hostable via Docker/Helm, with SDKs, OTel and integrations for LangChain, LlamaIndex, OpenAI and more.
Use Cases
Trace and debug LLM calls, retrieval and agent actionsRun LLM-as-a-judge and code-based evaluationsCentrally version and manage promptsCollect and analyze user feedback on outputsBuild datasets and run benchmark experimentsMonitor latency, cost and quality in productionSelf-host an LLMOps observability stackIterate on prompts and model configs in a playground
Built With
- Language
- TypeScript
- Frameworks
- LangChain · LlamaIndex · OpenAI SDK · Vercel AI SDK · LiteLLM · Haystack · Mastra · DSPy · Instructor · Next.js · ClickHouse
Tags
llm-observability · llm-evaluation · tracing · prompt-management · llmops · monitoring · self-hosted · datasets · playground · analytics · user-feedback · opentelemetry · clickhouse · evals · sdk · open-source