Langfuse
Open-source agent evals and observability platform: trace, evaluate and improve LLM applications and agents.
Tags
Description
Core is MIT ("MIT Expat"); code under ee/, web/src/ee/ and worker/src/ee/ is licensed separately under ee/LICENSE. Copyright is now held by ClickHouse, Inc.
Agent access
Related
- LangSmith: LangChain's agent and LLM observability and evaluation platform: tracing, monitoring, cost and latency tracking.
- Arize Phoenix: Open-source AI observability and evaluation platform from Arize.
- Langfuse MCP Server: Native, authenticated MCP server built into Langfuse so agents can read and write traces, prompts and other project data.
- Langfuse Skills: Agent Skills that teach coding assistants (Claude Code, Cursor, etc.) to work with Langfuse: traces, prompts, datasets, scores and migration.
- Langfuse Experiment Action: GitHub Action that runs a Langfuse experiment in your CI pipeline.
Guides & comparisons
- Evaluate an AI agent with open-source eval and observability tools (Guide): A hands-on loop for agent quality: instrument with OpenTelemetry, collect traces, turn real traces into a dataset, write code, LLM-as-judge and human evaluators, run offline experiments, then monitor production and gate pull requests in CI.
- Observability and eval platforms for AI agents (Comparison): Langfuse, LangSmith, Arize Phoenix, Braintrust, Opik and Laminar compared on license, self-hosting, OpenTelemetry ingestion, MCP access to your traces, free tiers, paid entry prices and built-in evaluation.
- Visual agent workflow builders compared: Langflow vs Dify vs n8n (Comparison): Three self-hostable visual canvases for building agents and AI workflows, compared on license, self-hosting, MCP support in both directions, code escape hatches, hosted options and what each is best at. Includes a note on Flowise, whose repo is archived.
- Agent benchmarks compared (Comparison): Ten widely cited agent benchmarks (SWE-bench, Terminal-Bench, tau-bench, BFCL, MCPMark, GAIA, BrowseComp, WebArena, Mind2Web and OSWorld) compared on what they measure, how many tasks they have, where the agent runs, how runs are scored, where results are published and how they are licensed.
- Bookkeeping agent stack (Stack): An agent that reconciles Stripe or Paddle revenue against the books in Xero, reads receipts and statements, and prepares draft entries for an accountant. It runs on read-only credentials, and every write needs a human.
- Data analysis agent stack (Stack): An agent that answers questions from your data: it queries DuckDB files, a ClickHouse warehouse or Postgres through read-only MCP servers, runs heavier analysis in a sandbox, reads spreadsheets and PDFs, and is tested and traced so you can trust the numbers.
- Agent that can buy things (Stack): The pieces for an agent that pays for APIs per call with x402 stablecoins and buys from merchants with controlled virtual cards, with spend limits, proof of user intent and a full audit trail.
- Research agent stack (Stack): An agent that searches the web and the scholarly record, reads full sources, runs analysis code in a sandbox and cites what it found, with tracing so you can audit how it got there.
Sources
- https://github.com/langfuse/langfuse
- https://langfuse.com
- https://langfuse.com/llms.txt
- https://raw.githubusercontent.com/langfuse/langfuse/main/LICENSE
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)