Hackernews posts about Langfuse

  1. Langfuse v4: agent evals and traces rebuilt on one immutable ClickHouse table (langfuse.com)
    3 points by JannikM 2 days ago | discuss
  2. Ask HN: Are there any production LLM pipeline setups to learn from?
    6 points by atif089 9 days ago | discuss
  3. How to build an eval set you can maintain (langfuse.com)
    8 points by lotteverh 2 days ago | discuss
  4. Scoping and curating AI eval datasets (langfuse.com)
    6 points by annabellschaf 11 days ago | discuss
  5. Traces Know What Broke. Your Agent Doesn't (memanto.ai)
    3 points by supportm 3 days ago | discuss
  6. Yes, you can copy our eval setup (langfuse.com)
    3 points by clemo_ra 29 days ago | discuss
  7. Good Evals Are Boring (langfuse.com)
    1 points by lotteverh 15 days ago | discuss
  8. Rust-lang/rust is adopting an LLM policy (blog.rust-lang.org)
    121 points by afdbcreid 16 days ago | 72 comments
  9. ClickHouse acquires Langfuse (langfuse.com)
    220 points by tin7in 7 months ago | 96 comments
  10. Launch HN: Langfuse (YC W23) – OSS Tracing and Workflows to Improve LLM Apps (github.com)
    215 points by mdeichmann over 1 year ago | 61 comments
  11. ClickHouse Acquires Langfuse (clickhouse.com)
    17 points by ramonga 7 months ago | discuss
  12. Langfuse Joins ClickHouse (langfuse.com)
    10 points by cnkk 7 months ago | 1 comments
  13. How we run untrusted code in Langfuse (OSS) and why we picked lambda (langfuse.com)
    4 points by marcklingen about 2 months ago | 3 comments
  14. Remote Code Execution on Langfuse with a single OTel trace request (aisafe.io)
    3 points by fedex_00 4 months ago | discuss
  15. LangChain vs. Langfuse: Key Differences and Their Role in LLM App Development (www.wizardlabs.com)
    3 points by cmdshepard about 1 year ago | discuss
  16. Trace your local Ollama model with Langfuse (langfuse.com)
    3 points by doener over 1 year ago | discuss
  17. Vulnerabilities in 45 Open Source Projects (vLLM, Langfuse, Phase, NocoDB) (www.kolega.dev)
    2 points by jfaganel99 6 months ago | 3 comments
  18. Langfuse v3 Infrastructure Evolution (langfuse.com)
    2 points by zzimbler over 1 year ago | discuss
  19. Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs (github.com)
    213 points by calcsam 7 months ago | 70 comments
  20. Launch HN: Cekura (YC F24) – Testing and monitoring for voice and chat AI agents
    89 points by atarus 6 months ago | 21 comments
  21. Open Source LLMOps Stack (oss-llmops-stack.com)
    64 points by marcklingen over 1 year ago | 7 comments
  22. Launch HN: Skope (YC S25) – Outcome-based pricing for software products
    55 points by benjsm 12 months ago | 45 comments
  23. Show HN: Pi Co-pilot – Evaluation of AI apps made easy (withpi.ai)
    34 points by achintms about 1 year ago | 8 comments
  24. Show HN: VoltAgent – Open-Source Observability-First TS AI Agent Framework (github.com)
    32 points by omeraplak over 1 year ago | 6 comments
  25. Show HN: Oodle.ai – $10 per million agent traces (www.oodle.ai)
    31 points by kirankgollu about 1 month ago | 12 comments
  26. Show HN: RLM-based local debugger for AI agent traces (github.com)
    27 points by mikepollard_dev about 2 months ago | 10 comments
  27. Segment for LLM Traces? Seeking Feedback on an Open Source LLM Log Router
    11 points by patethegreat over 1 year ago | 2 comments
  28. Show HN: How to analyze your LLM output – A behavioural health monitor for LLMs (splabs.io)
    10 points by k-thimmaraju 3 months ago | 7 comments
  29. Show HN: Lenzy AI – Turn AI agent conversations into actionable insights (www.lenzy.ai)
    8 points by BohdanPetryshyn 10 months ago | 7 comments
  30. Show HN: AgentBudget – Real-time dollar budgets for AI agents (github.com)
    7 points by sahiljagtapyc 6 months ago | 8 comments
  31. Ask HN: How are you monitoring AI agents in production?
    5 points by jairooh 6 months ago | 8 comments
  32. Show HN: I built an open source drag and drop editor for Genkit AI flows
    5 points by mfolaron 11 months ago | 2 comments
  33. Show HN: Verse AI – Catch the AI failures your evals miss (tryverse.ai)
    5 points by 4thabang 9 months ago | discuss
  34. Ask HN: How do you debug multi-step AI workflows when the output is wrong?
    4 points by terryjiang2020 6 months ago | 7 comments
  35. Show HN: Agent-triage – diagnosis of agent failures from production traces (github.com)
    4 points by oren1531 5 months ago | 2 comments
  36. Show HN: EvalsHub: Your AI is failing in production and you don't know it (www.evalshub.ai)
    4 points by neilsharma425 5 months ago | 1 comments
  37. Ask HN: What's the best way to build multi agent PoCs today
    4 points by bberenberg over 1 year ago | 1 comments
  38. Show HN: Dograh – voice agents that pick Recordings over TTS using LLM (github.com)
    4 points by a6kme 5 months ago | discuss