Find agent skills by outcome

v0.61.0 (2026-05-31)

- sdk: expose uselegacyattributes via Traceloop.init() (#4133)

services:

clickhouse:

Make sure to update the credential placeholders with your own secrets.

services:

services:

langfuse-web:

Untitled Skill

Security Policy

We strongly recommend using the latest version of Langfuse to receive all security updates.

Code Review Instructions

- ClickHouse migrations in the packages/shared/clickhouse/migrations/clustered directory should include ON CLUSTER default and should use Replicated merge tree table types.

x-redis-cluster-common-env: &redis-cluster-common-env

REDIS_PASSWORD: bitnami

services:

clickhouse:

!Langfuse GitHub Banner

CLAUDE.md

Langfuse is an open-source LLM engineering platform that helps teams collaboratively develop, monitor, evaluate, and debug AI applications.

!Langfuse GitHub Banner

First off, thanks for taking the time to contribute! ❤️

!Langfuse GitHub Banner

!Langfuse GitHub Banner

Dockerfile

.dockerignore

.agents/AGENTS.md

generic skill

See https://help.github.com/articles/ignoring-files/ for more about ignoring files.

/node_modules

public-hoist-pattern[]=prisma

public-hoist-pattern[]=@aws-sdk/client-s3

.nvmrc

v24.6.0

Generated code

packages/shared/prisma/generated

[codespell]

skip = .git,.pdf,.svg,package-lock.json,*.prisma,pnpm-lock.yaml,./worker/src/tests/chatml/framework-traces

site_name: LLM Guard

site_author: Protect AI, Inc.

Security Policy

We take the security of our software products seriously, which includes not only the code base but also the scanners provided within. If you have found any issues that might have security implications...

repos:

- repo: https://github.com/pre-commit/pre-commit-hooks