Langfuse
Open-source tracing and evals for LLM applications.
Key features
- Trace LLM calls, tool use, and retrieval steps
- Filter traces by user, session, cost, latency, or metadata
- Score outputs with model judges, rules, or human review
- Version prompts and deploy or roll them back
- Track cost, latency, and quality with dashboards and alerts
- Category
- Agents
- Who it's for
- Developers building production AI agents and LLM applications.
- Tags
- observabilityragevalshosting
- Website
- langfuse.com
- Listed
- 2026-09-15
Frequently asked questions
Is Langfuse free?
Langfuse has a free plan, with paid tiers for more usage or features.
How much does Langfuse cost?
Paid plans from $29/month, according to its pricing page.
What is Langfuse used for?
Open-source tracing and evals for LLM applications. Typical uses: trace LLM calls, tool use, and retrieval steps; filter traces by user, session, cost, latency, or metadata; score outputs with model judges, rules, or human review.
What are the best Langfuse alternatives?
Alternatives in the same category include Haystack, Agno, Browserbase, Flowise, LangChain.
Related in Agents
See all →- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.
- Agno Python framework for agents, formerly Phidata.
- Alter Privileged access for AI agents. Vaulted credentials, per-call policy, and an audit log. Free tier is 10,000 API calls a month.
- Amazon Bedrock AgentCore Serverless AgentCore Runtime in Amazon Bedrock for deploying and scaling AI agents.
- AutoGen Microsoft's framework for multi-agent conversations.
