SkillPedia Skills Encyclopedia
中文 EN

langfuselangfuse/langfuse

[Core Features]: An open-source AI engineering platform for agent observability and evaluation,…

No ratings yet Rate this skill
Stars37.6k
Forks4.3k
Watchers—
Open Issues—

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/langfuse/langfuse.git

OverviewOverview

[Core Features]: An open-source AI engineering platform for agent observability and evaluation, unifying every AI call and every agent in one place. Built on OpenTelemetry, it traces and evaluates agents, tracks usage and cost, uses production data to improve quality, and centrally manages prompts and skills. With an AI gateway, evals and prompt/skill management, it self-hosts in minutes or runs as Langfuse Cloud, battle-tested at scale. [Applicable Scenarios]: Debugging agent behavior and traces, monitoring token cost and call volume, versioning and A/B evaluating prompts and skills, turning production data into improvement signals. [Target Roles]: AI / Algorithm Engineer, Backend Engineer, QA Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID5940
Data sourceGitHub
Repositorylangfuse/langfuse
CategoryAI & Agent Skills / Agent Observability & Evaluation Platforms
Primary languageNot specified
LicenseNot specified
Default branch
GitHub repository ID
Rank#45 (position within the source ranking)
Site-wide popularity rank#55 (computed live from Stars, across all 5845 entries)

GrowthStar / Fork growth

Still collecting First record taken on 2026-11-19. Two days of data are needed before a trend line can be drawn.

TimelineTimeline

Repository created2026-11-19 12:20:374 hours ago
Data last updated2026-11-19 12:20:374 hours ago
Last commit—

CommitLatest commit

New Feature: feat(ai-gateway): default spend budgets for keys and users (#20440) * feat(ai-gateway): store per-key spend limits and return them from /resolve Co-authored-by: tobias.wochinger <tobias.wochinger@clickhouse.com> * feat(ai-gateway): enforce spend limits with Redis counters and Rust cost port Co-a

6dfeb60 Tobias Wochinger 2026-11-18

Next stepsNext steps