Langfuse
Langfuse is an open-source AI engineering platform for building and operating LLM applications. It brings together observability and tracing, evaluations, prompt management, datasets, an annotation workflow and a prompt playground, and integrates with OpenTelemetry, LangChain, the OpenAI SDK, LiteLLM and more. A Y Combinator (W23) company, it moved every product feature to the MIT license in 2025, so the only commercial pieces are thin enterprise-compliance add-ons such as SCIM, audit logs and project-level RBAC. The cloud free tier covers 50,000 units a month, with a $29/month Core plan for production traffic and higher tiers for longer retention and SOC 2/ISO reports. In January 2026 ClickHouse acquired Langfuse and publicly committed to keeping the MIT license and avoiding new pricing gates.
Work at Langfuse? Manage this listing
Our take
Langfuse is an open-source platform for the messy middle of LLM apps: tracing, evals, prompt management, datasets and a playground, all MIT-licensed and self-hostable. The free cloud tier is genuinely usable, and paid tiers add retention and compliance rather than gating features. ClickHouse acquired it in early 2026 and committed to keeping the license open.
Best for
Teams running LLM features in production who want to see what their app actually did, evaluate quality, and manage prompts without locking into a closed vendor.
Pros
- MIT-licensed; every core feature is open and self-hostable
- Tracing, evals, prompt management and datasets in one place
- Generous free cloud tier (50k units/month)
- Integrates with OpenTelemetry, LangChain, the OpenAI SDK and LiteLLM
Cons
- Self-hosting adds infrastructure to run
- Only compliance extras (SSO, audit logs, RBAC) are paid
- The observability and eval space is crowded
How it compares
Against Braintrust, Langfuse is open-source-first and cheaper to start; against tracing-only tools, it leans further into prompt management and production workflows.
Full review
Langfuse is an open-source AI engineering platform for building and operating LLM applications. It brings together observability and tracing, evaluations, prompt management, datasets, an annotation workflow and a prompt playground, and integrates with OpenTelemetry, LangChain, the OpenAI SDK, LiteLLM and more. A Y Combinator (W23) company, it moved every product feature to the MIT license in 2025, so the only commercial pieces are thin enterprise-compliance add-ons such as SCIM, audit logs and project-level RBAC. The cloud free tier covers 50,000 units a month, with a $29/month Core plan for production traffic and higher tiers for longer retention and SOC 2/ISO reports. In January 2026 ClickHouse acquired Langfuse and publicly committed to keeping the MIT license and avoiding new pricing gates.
Against Braintrust, Langfuse is open-source-first and cheaper to start; against tracing-only tools, it leans further into prompt management and production workflows.
Cloudkart Trust Graph
4.4/5- Actual Utility5/5
Source: Initial LLM-authored rubric (backfill)
- Ease of Use4/5
Source: Initial LLM-authored rubric (backfill)
- Pricing Fairness5/5
Source: Initial LLM-authored rubric (backfill)
- Reliability4/5
Source: Initial LLM-authored rubric (backfill)
- Differentiation4/5
Source: Initial LLM-authored rubric (backfill)
Scored as of . Each score is versioned and auditable; vendors cannot buy it.
How this score is set
- Editorial rubric
- Primary signal — five dimensions, 4.4/5 average.
- Community reviews
- None yet.
- Pricing verified
- Not yet verified
- Independence
- Score set by our editorial team before any affiliate relationship is considered. No vendor can buy it.
Frequently asked questions
- Is Langfuse free, and how much does it cost?
- Langfuse is open source and free to self-host.
- Who is Langfuse best for?
- Teams running LLM features in production who want to see what their app actually did, evaluate quality, and manage prompts without locking into a closed vendor.
- How is Langfuse rated on Cloudkart.ai?
- Langfuse scores 4.4 out of 5 on the Cloudkart.ai rubric, which weighs actual utility, ease of use, pricing fairness, reliability and differentiation. Scores are set editorially and can never be bought.
Community reviews
No community reviews yet. Be the first to share how Langfuse works for you.
Relevant tools
More tools in Data & Analytics AI.
Streamlit
Open-source Python framework for building and sharing interactive data and AI/ML apps with minimal front-end code.
Metabase
Open-source business-intelligence and embedded-analytics tool with a no-code query builder usable with or without SQL.
Lightdash
AI-first, open-source BI platform that is dbt-native, reading metric definitions directly from your dbt project.
Firecrawl
Web data API that searches, scrapes, crawls, and extracts clean, LLM-ready structured data from any website for AI agents.
Compare Langfuse head-to-head: vs Streamlit · vs Metabase · vs Lightdash · vs Firecrawl