Langfuse: Open Source Agent Evals & Observability

langfuse.com

Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

AI / ML DevOps / SRE / infrastructure

’23 ’24 ’25 ’26

Posts: 869 from 19 Jul 2023 to 22 Oct 2026
Posting: weekly (35 in the last year)
Kind: company blog

2026 29

22 OctannouncementLangfuse Cloud Japan RegionLangfuse Cloud Japan is live. A dedicated cloud region hosted in Japan for teams that need their LLM observability data to stay in Japan.Apr 27, 2026·Marc, Clemens, Max
22 OctengineeringClassifying User Intent with Categorical LLM-as-a-JudgeA guide on how to set up a categorical LLM-as-a-judge evaluator to classify user intent. Follow along with how we applied this to our demo application.Apr 14, 2026·Lotte
21 OctengineeringUsing TypeSafe's Jev for evalsA specialized decision model for routing, classification, and eval verdicts — and how to score production traces with Jev-as-a-judge in Langfuse.Sep 18, 2026·Annabell, Hassieb
30 SepannouncementLangfuse Cloud 日本リージョンを開始しましたLangfuse Cloud 日本リージョンを公開しました。LLM のトレースや評価データを日本国内に保管したいチーム向けの専用クラウドリージョンです。Apr 27, 2026·Marc, Clemens, Max
23 SepengineeringCatching conversation signals in LangfuseScore every chat agent conversation for frustration, corrections, follow-ups, and resolution — in one Jev pass, at a fraction of LLM-as-a-judge cost.Sep 23, 2026·Annabell
18 SepengineeringHow we built Langfuse HaloHow we built Langfuse Halo, our powerful in-app assistant, on our existing MCP server, why the agent runs outside its sandbox, and how we handle background runs.Oct 21, 2026·Ben
31 AugengineeringHow we use agents to review production infrastructureHow repo-owned agent workflows help us review incidents, infra cost, security findings, and bugs in production.Jun 5, 2026·Max
31 JulengineeringAI is eating the AI engineering loopThe full AI engineering loop can technically be automated now. But that doesn't mean it should. Here is what we think you should hand to agents, and what you should keep doing yourself.Jun 9, 2026·Lotte
22 JulengineeringDesigning the runtime for Langfuse code evaluatorsCode evaluators let you score traces with your own Python or TypeScript code. A look at the execution model behind them: the requirements, the options we rejected, and the security stance we adopted.Jun 22, 2026·Tobias
15 JulguideBuilding Deployment Gates for LLMs and AI Agents in Financial ServicesHow we used Langfuse datasets, experiments, and the public API to build automated pass/fail deployment gates for LLMs and AI agents in financial services.Jul 15, 2026·Doneyli
15 JulAI Agent Observability, Tracing & Evaluation with Langfuse - Langfuse
13 JulComparing Open-Source AI Agent Frameworks - Langfuse
22 JunengineeringYes, you can copy our eval setupEvals need to be custom to your app. At least some of them. A good chunk you can, and should be copying. Here is our setup for our docs chatbot.Jul 22, 2026·Annabell
9 Junguide, architectureProvisioning and governing Langfuse across teamsChoose project boundaries, provision access, and verify safe, useful telemetry as more application teams adopt Langfuse.Oct 22, 2026·Boris, Doneyli
9 JunengineeringWe launched Halo 😇We launched Halo, the assistant inside Langfuse. It can investigate traces, help set up evals, build dashboards, and take action with your approval.Oct 23, 2026·Lotte
5 Junguide, architectureOperating Langfuse as an internal serviceCoordinate SDK upgrades, monitor service health, and support evaluation workflows, access reviews, and cost allocation across application teams.Oct 22, 2026·Boris, Doneyli
31 MayupdateLangfuse April UpdateJapan Cloud Region, new Experiments, Langfuse Academy, LLM-as-a-Judge API and moreApr 30, 2026·Marc
30 AprupdateLangfuse May UpdateCode Evaluators, full-text search, Langfuse MCP, Experiments in CI/CD and moreMay 31, 2026·Marc
27 AprupdateLangfuse August UpdateLangfuse v4, new evaluator setup flow, multi-modal evaluators, CLI 1.0, responsive timeline and moreAug 31, 2026·Marc
27 AprupdateLangfuse July UpdateChart any table, dashboards via API, CLI, and MCP, new graph view modes, media previews and moreJul 31, 2026·Marc
14 AprupdateLangfuse September UpdateJev-as-a-judge, Halo sandbox, rebuilt experiment results, evaluator backfills and moreSep 30, 2026·Marc
1 AprHigh-Signal Monitoring for AI Support Agents - Langfuse
31 MarLangfuse March Update - Langfuse
24 MarWhat Autoresearch Taught Us About Tests - Langfuse
13 MarAn Agent Skill That Synthesizes Feedback - Langfuse
28 FebLangfuse February Update - Langfuse
26 FebEvaluating AI Agent Skills - Langfuse
16 FebUsing Agent Skills to Automatically Improve your Prompts - Langfuse
31 JanLangfuse January Update - Langfuse

Langfuse: Open Source Agent Evals & Observability

2026 29

2025 28

2024 51

2023 32

Undated 729