langfuse /langfuse
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
★ 37,453⑂ 4,236👁 111⑃ 13,122● 3,282▤ 742
+26
日增长
+275
周增长
37,453
stars
4,236
forks
111
watchers
13,122
prs
3,282
issues
742
releases
README
Langfuse Cloud
·
Self-Host
·
Demo
Docs ·
Report Bug ·
Feature Request ·
Changelog ·
Roadmap
Langfuse is an open source AI engineering platform for agent evals and observability. It is one open platform for every AI call your company makes and every agent your teams build: track usage and costs, trace and evaluate agents, and use production data to ship better AI. Use Langfuse Cloud or self-host in minutes; Langfuse is battle-tested at scale.
Watch a quick demo of the project here:
🧑💻 We're hiring
Interested in contributing to Langfuse full-time? Langfuse is growing fast (we doubled the team in the last 6 months). Since January 2026 we're part of ClickHouse. We hire remotely, with offices in Berlin, San Francisco, Amsterdam, and New York.
See open roles →
✨ Core Features
- AI Observability: Instrument your app and start ingesting traces to Langfuse, thereby tracking LLM calls and other relevant logic in your app such as retrieval, embedding, or agent actions. Inspect and debug complex logs and user sessions. Built on OpenTelemetry. Try the interactive demo to see this in action.
- Prompt Management helps you centrally manage, version control, and collaboratively iterate on your prompts. Thanks to strong caching on server and client side, you can iterate on prompts without adding latency to your application. The LLM Playground lets you test prompts and model configurations; when you see a bad result in tracing, you can jump straight to the playground to iterate on it.
- Skill Management (beta) brings versioning and labels to agent skills: a SKILL.md with task instructions plus optional supporting files. Promote or roll back versions without changing application code, and link skill versions to the traces they produced.
- Evaluations are key to the AI agent development workflow, and Langfuse adapts to your needs. It supports LLM-as-a-judge, code evaluators, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs. Use Datasets and Experiments to build test sets and benchmarks for pre-deployment testing and continuous improvement.
- AI Gateway (beta) gives your organization one endpoint for calls to your model providers. Keep provider credentials in one place, hand out per-user or service account gateway keys, approve models centrally, track AI spend per user, key, and model, and record every call as a Langfuse trace.
- Metrics and Dashboards: Track latency, cost, and quality across any dimension with custom dashboards, the metrics API, and alerts.
- Comprehensive API: Langfuse is frequently used to power bespoke AI engineering workflows while using the building blocks provided by Langfuse via the API. An OpenAPI spec, typed SDKs for Python and JS/TS, the Langfuse CLI,Top issues
#12738MCP Server: Support SSO/OIDC authentication as alternative to static API keys45 comments · 2026-03-23#8020bug: Possible Gemini token/cost mismatch in Langfuse (using Google SDK)30 comments · 2025-07-22#7913bug: Path: projects.environmentFilterOptions27 comments · 2025-07-16#7995bug: `TypeError: Cannot set property message of ZodError` during startup of Web pod24 comments · 2025-07-21#6504bug: Automatic Media Upload Fails with Self-Hosted Langfuse and GCS24 comments · 2025-04-17#4675bug: `TypeError: Cannot set property message of` in nextjs initialization22 comments · 2024-12-10#16077bug: v4 unified Tracing table cannot display trace total cost — root SPAN rows show $0.0021 comments · 2026-08-13#8316bug: conflict between Langfuse's OpenTelemetry instrumentation and Google ADK's context management20 comments · 2025-08-05
Discussions
#20248Contributing a privacy feature to the Langfuse community0 comments · 2026-11-15#20205Bedrock LLM3 comments · 2026-11-13#20178A subscription plan for people with low income0 comments · 2026-11-13#20166Manage alerts (monitors) through the public API0 comments · 2026-11-12#20163Add Prompt Description Field and Text in UI0 comments · 2026-11-12#20141Add newest-first sort toggle for traces in session view and annotation queue items1 comments · 2026-11-12#20137Setting permissions for API keys in v3.225.21 comments · 2026-11-12#20097Langfuse self hosted v3 with clickhouse 26.10.3.7 compatibility and upgrade path2 comments · 2026-11-11
Latest release
v4.80.0 v4.80.0 2026-11-13What's Changed Features feat(clickhouse): send query parameters in the request body by default by @Steffen911 in https://github.com/langfuse/langfuse/pull/20049 feat(ai-gateway): add Google AI Studio as a gateway provider by @wochinge in https://github.com/langfuse/langfuse/pull/20086 feat(ai-gateway): rename to Connections & Models and hide Models tab without connections by @wochinge in https://github.com/langfuse/langfuse/pull/20112 feat(in-app-agent): add "Copy session link" to Halo's session menu and hide session links in HIPAA by @nimarb in https://github.com/langfuse/langfuse
相关报道 (7)
GIGAZINEAIエージェントが実際にどのように動いてトークンを使っているかが後から見てわかるようにできる「Langfuse」、オープンソースで ...2026-08-23腾讯网ClickHouse收购Langfuse:数据平台竞相掌控AI反馈循环2026-01-26https://www.80aj.com/Agent 自我改进真正卡在哪:Langfuse 给出一套开源闭环2026-10-07www.80aj.comLangfuse:AI Agent 时代的可观测基础设施2026-05-2236氪起底千亿估值数据库黑马:字节阿里腾讯微软特斯拉都在用2026-02-05InfoQ.cnClickHouse 完成由Dragoneer 领投的4 亿美元D 轮融资,加速其在分析与AI 基础设施领域的扩张2026-01-2051CTO2025年AI Builder 工具箱:20 个开源神器让你效率飙升2025-09-08
News & coverage (4)
Hacker NewsLaunch HN: Langfuse (YC W23) – OSS Tracing and Workflows to Improve LLM Apps▲ 215 · 61 comments · 2024-12-17Hacker NewsShow HN: Langfuse – Open-source observability and analytics for LLM apps▲ 143 · 35 comments · 2023-08-29aimultiple.com15 AI Agent Observability Tools: AgentOps & Langfuse2026-10-14marktechpostTop LLM Observability and Evaluation Platforms in 2026: Langfuse, LangSmith, Braintrust, Arize, and More Compared2026-08-09