Artificial Intelligencedocker-readypermissive-license
Langfuse: the best Open Source alternative to Datadog LLM Observability in 2026
Langfuse is an open source observability and evaluation platform for LLM applications: traces, per-request costs, evaluation datasets and prompt management, self-hostable alongside your AI stack.
Technical profile
- License
- MIT
- Category
- Artificial Intelligence
- Replaces
- Datadog LLM Observability
- Tech stack
- TypeScriptNext.jsPostgreSQLClickHouse
Preview
Public image provided by Langfuse on its own website.
Key features
- Detailed traces for every LLM call
- Prompt management with versioning
- Datasets and automatic evaluations
Langfuse vs. Datadog LLM Observability
Pros
- MIT core, with optional separate enterprise features
Things to consider
- Large-scale deployment adds ClickHouse and Redis
Quick Docker installation guide
Copy this docker-compose.yml, adjust the example passwords and run docker compose up -d on your server. See the full step-by-step guide →
docker-compose.yml
version: "3.9"
services:
langfuse:
image: langfuse/langfuse:latest
restart: unless-stopped
ports:
- "3000:3000"
environment:
- DATABASE_URL=postgresql://langfuse:langfuse@langfuse-db:5432/langfuse
- NEXTAUTH_SECRET=change-me-super-secret
- SALT=change-me-salt
depends_on:
- langfuse-db
langfuse-db:
image: postgres:15-alpine
restart: unless-stopped
environment:
- POSTGRES_USER=langfuse
- POSTGRES_PASSWORD=langfuse
- POSTGRES_DB=langfuse
volumes:
- langfuse_pg_data:/var/lib/postgresql/data
volumes:
langfuse_pg_data: