--- title: Why is Langfuse Open Source? description: Langfuse strives to be the most open and transparent LLM toolkit. Learn more about why open source is important to us. --- # Why is Langfuse open source? We believe in the power of open source and community collaboration for several reasons: - **Transparency & Trust**: Developers can inspect every line that handles their data, audit security practices, and avoid vendor lock-in. - **Community Collaboration**: The open source community moves quickly and accelerates [integrations](/integrations) with LangChain, LiteLLM, OpenTelemetry, and the next library you'll build tomorrow. Join our community on [GitHub Discussions](/ideas) to shape the [roadmap](/docs/roadmap). - **Faster Innovation**: Shared ownership means bugs are squashed and features land sooner. - **Sovereignty**: You can run Langfuse anywhere — from your laptop to an air-gapped cluster — without hitting artificial usage caps. [Self-host](/self-hosting) it on your own infrastructure. - **Extensible**: All data is accessible via the public [API](/docs/api) which is fully tested. You can wrap/extend Langfuse or build your own workflows and AI platform around it. ## Licensing Overview Langfuse is built in the open. We believe open source and sustainable commercialization can coexist—and this strategy is how we fund continuous, community-driven innovation that's adopted across startups and enterprises. Do you have any questions? Please reach out to the maintainers via [GitHub Discussions](/gh-support). All product capabilities—tracing, evaluations, prompt management, experiments, annotation, the playground, and more—are MIT licensed without any usage limits. Enterprise modules such as SCIM, audit logging, and data retention policies require a commercial license when you self-host Langfuse. Self-hosting keeps data within your infrastructure; Cloud offloads operational overhead. Because every deployment runs the same codebase and schema, **you can switch between OSS, Enterprise self-host, and Langfuse Cloud at any time**. Add or remove a license key or switch to the Langfuse Cloud endpoints. No feature flags to untangle, no vendor lock-in, and no downtime. | | OSS Self-Host | Enterprise Self-Host | Langfuse Cloud | | ----------------------------------------------- | ------------- | -------------------- | -------------- | | All Product Features | ✅ | ✅ | ✅ | | [Enterprise Add-ons](/self-hosting/license-key) | - | ✅ | ✅ | | Fully Managed Service | - | - | ✅ | ### Langfuse OSS Langfuse's OSS includes all product features and has no usage limits. Fork it, extend it, ship it—even in commercial products. All core APIs and backend logic scale horizontally out-of-the-box, so the same deployment can grow from a single-node Docker Compose to a multi-node Kubernetes cluster—without code changes or feature gates. It's the same architecture that powers Langfuse Cloud. ### Commercial Extensions Enterprise Edition (EE) modules live in clearly marked `/ee` directories. These are shipped as source code, but require a [license key](/self-hosting/license-key) to run. They are optional; the core works 100% without them. ## Architecture Consistency & Scale The Langfuse deployment stack is exactly the same for OSS, Enterprise self-host, and Langfuse Cloud. See our [Self-Hosting Guide](/self-hosting) for instructions on running Langfuse locally and deployments at production scale.
Architecture ```mermaid flowchart TB User["UI, API, SDKs"] subgraph vpc["VPC"] Web["Web Server
(langfuse/langfuse)"] Worker["Async Worker
(langfuse/worker)"] Postgres@{ img: "/images/logos/postgres_icon.svg", label: "Postgres - OLTP\n(Transactional Data)", pos: "b", w: 60, h: 60, constraint: "on" } Cache@{ img: "/images/logos/redis_icon.png", label: "Redis\n(Cache, Queue)", pos: "b", w: 60, h: 60, constraint: "on" } Clickhouse@{ img: "/images/logos/clickhouse_icon.svg", label: "Clickhouse - OLAP\n(Observability Data)", pos: "b", w: 60, h: 60, constraint: "on" } S3@{ img: "/images/logos/s3_icon.svg", label: "S3 / Blob Storage\n(Raw events, multi-modal attachments)", pos: "b", w: 60, h: 60, constraint: "on" } end LLM["LLM API/Gateway
(optional; BYO; can be same VPC or VPC-peered)"] User --> Web Web --> S3 Web --> Postgres Web --> Cache Web --> Clickhouse Web -..->|"optional for playground"| LLM Cache --> Worker Worker --> Clickhouse Worker --> Postgres Worker --> S3 Worker -..->|"optional for evals"| LLM ``` Langfuse consists of two application containers, storage components, and an optional LLM API/Gateway. - [**Application Containers**](/self-hosting/deployment/infrastructure/containers) - Langfuse Web: The main web application serving the Langfuse UI and APIs. - Langfuse Worker: A worker that asynchronously processes events. - **Storage Components**: - [Postgres](/self-hosting/deployment/infrastructure/postgres): The main database for transactional workloads. - [Clickhouse](/self-hosting/deployment/infrastructure/clickhouse): High-performance OLAP database which stores traces, observations, and scores. - [Redis/Valkey cache](/self-hosting/deployment/infrastructure/cache): A fast in-memory data structure store. Used for queue and cache operations. - [S3/Blob Store](/self-hosting/deployment/infrastructure/blobstorage): Object storage to persist all incoming events, multi-modal inputs, and large exports. - [**LLM API / Gateway**](/self-hosting/deployment/infrastructure/llm-api): Some features depend on an external LLM API or gateway. Langfuse can be deployed within a VPC or on-premises in high-security environments. Internet access is optional. See [networking](/self-hosting/security/networking) documentation for more details.
## Frequently Asked Questions [#enterprise-edition-ee-faq]
Is Langfuse really open source? Yes. Everything outside the `/ee` folders is MIT-licensed — an OSI-approved license. You get the four freedoms: use, study, modify, distribute.
Will I accidentally use EE features? No. EE packages are isolated and gated by the license key check. You can run the core image without a key without running EE code.
Which self-host licensing options exist? All product features are freely available under the MIT license. A commercial Enterprise license is only required for advanced security capabilities such as SCIM, extended audit logging, and data retention policies (see [pricing page](/pricing-self-host)). You can add a [license key](/self-hosting/license-key) to your deployment to enable these features at any time.
Does Langfuse rely only on open-source components? Yes. The entire stack is open source and can be self-hosted. Find a complete list in the configuration files across our repositories: - Langfuse server: monorepo with [multiple `package.json` files](https://github.com/search?q=repo%3Alangfuse%2Flangfuse%20package.json&type=code) - Langfuse Python SDK: main [`pyproject.toml`](https://github.com/langfuse/langfuse-python/blob/main/pyproject.toml) - Langfuse JS SDK: monorepo with [multiple `package.json` files](https://github.com/search?q=repo%3Alangfuse%2Flangfuse-js%20package.json&type=code) As the core Langfuse server is most actively developed, we run an [automated license check](https://github.com/langfuse/langfuse/actions/workflows/licensecheck.yml) on every change to avoid adding dependencies with non-permissive licenses. If you find any issues, please let us know.
What's the release cadence and how do I stay up to date? We cut a **GitHub Release multiple times a week** (tagged `vX.Y.Z`) and publish detailed notes in the [changelog](https://github.com/langfuse/langfuse/releases). Langfuse Cloud is always running the latest version; self-host users can pull the identical Docker image tag to stay up to date or upgrade on their own schedule ([docs](/self-hosting/upgrade)).
Does the OSS build phone home? Can I disable telemetry? By default, Langfuse OSS sends **aggregated usage telemetry** (no personal data) so we can improve the product. **No traces, prompts, or customer data leave your cluster.** You can disable it via `TELEMETRY_ENABLED=false` (details in the [telemetry docs](/self-hosting/security/telemetry)).
Can I run Langfuse completely offline / air-gapped? Yes. After the initial image pull, Langfuse **does not require any outbound network calls** to work. Teams in regulated environments run it inside air-gapped Kubernetes clusters; just disable telemetry as above and mirror the Docker registry locally.
How do I contribute? Here are the best ways to contribute to Langfuse via GitHub: 1. Submit and vote on [Ideas](/ideas). 2. Create and comment on [Issues](/issues). 3. Create a pull request. See [Contributing.md](https://github.com/langfuse/langfuse/blob/main/CONTRIBUTING.md) to get started.
I want to see the code! All our repositories are on [GitHub](https://github.com/langfuse): - Langfuse Server (UI and API): [`langfuse/langfuse`](https://github.com/langfuse/langfuse) - Langfuse Python SDK and integrations: [`langfuse/langfuse-python`](https://github.com/langfuse/langfuse-python) - JS SDK and integrations: [`langfuse/langfuse-js`](https://github.com/langfuse/langfuse-js) - Docs: [`langfuse/langfuse-docs`](https://github.com/langfuse/langfuse-docs)
Can you share some public metrics on how widely Langfuse is used? Sure, we summarized some statistics in [this blog post](/blog/2024-11-most-used-oss-llmops) and in the dashboard below. [View the Langfuse public metrics dashboard](https://app.hex.tech/clickhouse-analytics/app/0349rZiOtG8QDXATQrRCSI/latest).
--- ## Agent Instructions This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/handbook/chapters/open-source.md`. ### Querying these docs If the answer is not on this page, query the documentation instead of guessing: - **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question: ```bash curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?" ``` - **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt). ### Before writing Langfuse code - **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results. - **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application. - **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples. - **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .