langfuse/langfuse
Open-source LLM engineering platform: tracing, evals, prompt management, and metrics for agent systems. The observability layer most stacks standardize on. Agentiquette scores it 80/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Evaluation / observability |
|---|---|
| License | NOASSERTION |
| Maintainer | Langfuse |
| Compatible agents | generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 30,607 stars · 3,210 forks · 686 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-07 |
| Created | 2023-05-18 |
Editorial analysis
Observability is the loop-reliability axis most teams skip, and this is the least-painful way to stop skipping it. Traces attach evals to real production runs, which quietly delivers the thing standalone eval tools cannot: scores on the distribution you actually serve. Self-host story is genuine, license nuance noted.
Risks
Core is MIT-licensed but the repo carries a mixed license (enterprise features); read the license map before self-hosting commercially.
Evidence notes: Maintenance: same-day commits. Eval readiness: scores-on-traces closes the production feedback loop. Docs: integration guides per framework, accurate at fetch.
Install and first run
docker compose up # or pip install langfuse for the SDKAlternatives in this category
Test harness for prompts, agents, and RAG pipelines: declarative test cases, assertions, matrix comparisons, and red-team scanning, runnable…
A pytest-style LLM evaluation framework: metric classes for correctness, hallucination, RAG quality, and agent task completion, written as…
OpenAI's original eval framework and benchmark registry. Historically foundational; maintenance has visibly slowed as evaluation moved into…
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/langfuse)Frequently asked questions
Is langfuse/langfuse good?
langfuse/langfuse scores 80/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is langfuse/langfuse for?
Open-source LLM engineering platform: tracing, evals, prompt management, and metrics for agent systems. The observability layer most stacks standardize on.
Is langfuse/langfuse maintained?
Last commit 2026-07-07, 686 open issues at fetch time (2026-07-07). Maintenance is scored at 92 of 100.
Maintainer of langfuse/langfuse? Claim this listing and suggest corrections.