{"slug": "langfuse", "name": "Langfuse", "category": "observability", "category_name": "Monitoring and analytics", "description": "", "recommenders": 3, "commenters": 6, "warners": 0, "score": 3.344, "rising": 0.35, "first": "2026-01-29", "latest": "2026-10-28", "why": "Langfuse ended up being the observability tool I went with instead over the one I built", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 2, "warn": 0}, "spark": [0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Langfuse ended up being the observability tool I went with instead over the one I built", "icon": true, "domain": "langfuse.com", "github_repo": null, "official_url": "https://langfuse.com", "pricing": "", "aliases": ["Langfuse"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 786973991, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "Langfuse tracing on every token and dollar.", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "LLM tracing", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 776285312, "item_id": 48517832, "url": "https://news.ycombinator.com/item?id=48517832", "by": "spmurrayzzz", "date": "2026-06-13", "stance": "recommend", "quote": "Langfuse ended up being the observability tool I went with instead over the one I built", "excerpt": "I used it, but only briefly to evaluate it. It had some overlap with a tool I built myself, was curious if any of the extra features would be useful. Ultimately I found the data model and UI to be both cumbersome and unintuitive. Langfuse ended up being the observability tool I went with instead over the one I built (and still use today).", "context": "built their own similar tool", "use_case": "LLM observability", "switched_from": "TensorZero", "story": "AI OSS tool repo goes archived over night after raising $7.3M Seed"}, {"id": 749017345, "item_id": 46813584, "url": "https://news.ycombinator.com/item?id=46813584", "by": "Roark66", "date": "2026-01-29", "stance": "recommend", "quote": "I'm quite happy with this.", "excerpt": "I use litellm (slightly modified to allow cloud code telemetry pass through) and langfuse. There is no need for MitM, you can set Api base address to your own proxy in all the coding assistants (at least all I know - Claude Code, opencode, gemini, vc plugin). The changes I made allow use of the models endpoint in litellm at the same base url as telemetry and passing through Claude Max auth. This is not about using yo", "context": "", "use_case": "recording LLM tool calls", "switched_from": "", "story": "A MitM proxy to see what your LLM tools are sending"}]}], "caveats": [], "who": [{"by": "Gayithri2026", "context": "AI engineer building RAG chatbots", "url": "https://news.ycombinator.com/item?id=49185874", "date": "2026-08-05"}, {"by": "spmurrayzzz", "context": "built their own similar tool", "url": "https://news.ycombinator.com/item?id=48517832", "date": "2026-06-13"}, {"by": "Intendant", "context": "AI agent platform engineer seeking work", "url": "https://news.ycombinator.com/item?id=48364468", "date": "2026-06-01"}], "tags": [], "use_cases": ["llm observability", "llm tracing", "llm observability tool evaluation", "recording llm tool calls"], "compared": [{"slug": "tensorzero", "name": "TensorZero", "co": 1, "switched_from": 1, "switched_to": 0}], "makers": [{"id": 786881408, "item_id": 49180088, "url": "https://news.ycombinator.com/item?id=49180088", "by": "mdeichmann", "date": "2026-08-05", "stance": "recommend", "quote": "Langfuse is the open-source LLM engineering platform \u2014 tracing/observability, evals, and prompt management", "excerpt": "Langfuse (now part of ClickHouse) | Product Engineers & Backend Engineers | Berlin / EU-remote, ~1 week onsite every 2 months (travel covered) | Full-time | \u20ac70\u2013130k + ClickHouse equity Hi, I'm Max, CTO and co-founder. Langfuse is the open-source LLM engineering platform \u2014 tracing/observability, evals, and prompt management \u2014 used by tens of thousands of teams to ship, debug, and improve their LLM and agent apps. Ear", "context": "CTO and co-founder", "use_case": "LLM observability", "switched_from": "", "story": "Ask HN: Who is hiring? (August 2026)"}], "threads": [{"url": "https://news.ycombinator.com/item?id=50257116", "title": "Ask HN: Has anyone used Phoenix, Langfuse, or OpenObserve?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49156682", "title": "Ask HN: Who wants to be hired? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49156683", "title": "Ask HN: Who is hiring? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48516504", "title": "AI OSS tool repo goes archived over night after raising $7.3M Seed", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48357724", "title": "Ask HN: Who wants to be hired? (June 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46975123", "title": "Vulnerabilities in 45 Open Source Projects (vLLM, Langfuse, Phase, NocoDB)", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 1}, "2026-02": {"compare": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"neutral": 1, "recommend": 1}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"compare": 1}}, "quotes": [{"id": 804332768, "item_id": 50270798, "url": "https://news.ycombinator.com/item?id=50270798", "by": "jack_bing", "date": "2026-10-28", "stance": "compare", "quote": "I used both Langfuse and Logfire. Imo both very similar", "excerpt": "I used both Langfuse and Logfire. Imo both very similar, and at the same time limited when you want to customize graphs. Langfuse in general has broder feature set (however I used Logfire long time ago so it might have changed) like evaluation and prompt management", "context": "", "use_case": "LLM observability", "switched_from": "", "story": "Ask HN: Has anyone used Phoenix, Langfuse, or OpenObserve?"}, {"id": 786973991, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "Langfuse tracing on every token and dollar.", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "LLM tracing", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 776285312, "item_id": 48517832, "url": "https://news.ycombinator.com/item?id=48517832", "by": "spmurrayzzz", "date": "2026-06-13", "stance": "recommend", "quote": "Langfuse ended up being the observability tool I went with instead over the one I built", "excerpt": "I used it, but only briefly to evaluate it. It had some overlap with a tool I built myself, was curious if any of the extra features would be useful. Ultimately I found the data model and UI to be both cumbersome and unintuitive. Langfuse ended up being the observability tool I went with instead over the one I built (and still use today).", "context": "built their own similar tool", "use_case": "LLM observability", "switched_from": "TensorZero", "story": "AI OSS tool repo goes archived over night after raising $7.3M Seed"}, {"id": 773831490, "item_id": 48364468, "url": "https://news.ycombinator.com/item?id=48364468", "by": "Intendant", "date": "2026-06-01", "stance": "neutral", "quote": "I stood up their first LLM observability stack, Langfuse on AWS EKS", "excerpt": "Location: Austin, TX Remote: Yes (5+ yrs fully remote) Willing to relocate: Yes, for the right role Open to: Full-time or contract Technologies: Claude Agent SDK, MCP (author + consumer), RAG, evals, Langfuse, LLM-ops; AWS (EKS, Lambda, Bedrock) + Azure (AKS, ADO); Databricks, Terraform, Kubernetes; Python, TypeScript, Rust R\u00e9sum\u00e9: https://drive.google.com/file/d/13j_Ax_0soXWrtoMfFORqV4A34knNGXEg/view LinkedIn: linke", "context": "AI agent platform engineer seeking work", "use_case": "LLM observability", "switched_from": "", "story": "Ask HN: Who wants to be hired? (June 2026)"}, {"id": 752088192, "item_id": 47005512, "url": "https://news.ycombinator.com/item?id=47005512", "by": "jelpern", "date": "2026-02-13", "stance": "compare", "quote": "Using LangFuse as an example, since that is one of the tools I'm considering", "excerpt": "I am evaluating AI tools. How should I use this research to interpret a tool's vulnerability profile as part of the selection process? Using LangFuse as an example, since that is one of the tools I'm considering: this project has four vulnerabilities\u2014is that a red flag, or does the maintainers' response determine whether it's acceptable? What metrics should I weigh: vulnerability count, severity, response time, remed", "context": "evaluating AI tools", "use_case": "LLM observability tool evaluation", "switched_from": "", "story": "Vulnerabilities in 45 Open Source Projects (vLLM, Langfuse, Phase, NocoDB)"}, {"id": 749017345, "item_id": 46813584, "url": "https://news.ycombinator.com/item?id=46813584", "by": "Roark66", "date": "2026-01-29", "stance": "recommend", "quote": "I'm quite happy with this.", "excerpt": "I use litellm (slightly modified to allow cloud code telemetry pass through) and langfuse. There is no need for MitM, you can set Api base address to your own proxy in all the coding assistants (at least all I know - Claude Code, opencode, gemini, vc plugin). The changes I made allow use of the models endpoint in litellm at the same base url as telemetry and passing through Claude Max auth. This is not about using yo", "context": "", "use_case": "recording LLM tool calls", "switched_from": "", "story": "A MitM proxy to see what your LLM tools are sending"}]}