Langfuse’s Open-Source Strategy
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.
All the interfaces and backend services that make up Langfuse’s core are released under the permissive MIT license without any usage limits. Peripheral, enterprise-grade capabilities (e.g. advanced human annotation pipelines, enhanced RBAC, audit logging) are available under a commercial license when you self-host Langfuse.
Why is Langfuse open source?
- 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 with LangChain, LiteLLM, OpenTelemetry, and the next library you’ll build tomorrow. Join our community on GitHub Discussions to shape the 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 it on your own infrastructure.
- Extensible: All data is accessible via the public API which is fully tested. You can wrap/extend Langfuse or build your own workflows and AI platform around it.
Licensing Overview
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 | Pro / Enterprise Self-Host | Langfuse Cloud | |
|---|---|---|---|
| All Core features | ✅ | ✅ | ✅ |
| EE add-ons | - | ✅ | ✅ |
| Fully managed service | - | - | ✅ |
MIT Core
Langfuse’s OSS core includes all core 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 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 for instructions on running Langfuse locally and deployments at production scale.
Architecture
Langfuse consists of two application containers, storage components, and an optional LLM API/Gateway.
- Application Containers
- Langfuse Web: The main web application serving the Langfuse UI and APIs.
- Langfuse Worker: A worker that asynchronously processes events.
- Storage Components:
- Postgres: The main database for transactional workloads.
- Clickhouse: High-performance OLAP database which stores traces, observations, and scores.
- Redis/Valkey cache: A fast in-memory data structure store. Used for queue and cache operations.
- S3/Blob Store: Object storage to persist all incoming events, multi-modal inputs, and large exports.
- LLM API / Gateway: 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 documentation for more details.
Frequently Asked Questions
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?
Langfuse offers two paid tiers atop the free OSS core (see pricing page):
- Pro (self-serve) - an online, pay-as-you-go license that unlocks all Enterprise Edition (
/ee) code for small teams. Purchase instantly from the dashboard and cancel anytime. - Enterprise (custom contract) - the same EE feature set plus advanced SAML/SCIM SSO, extended audit-log retention, priority support & SLAs, red-lined legal terms, and optional professional-services assistance.
Upgrading is as simple as setting LANGFUSE_EE_LICENSE_KEY (docs) in your deployment; containers pick up the change at runtime.
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.jsonfiles - Langfuse Python SDK: main
pyproject.toml - Langfuse JS SDK: monorepo with multiple
package.jsonfiles
As the core Langfuse server is most actively developed, we run an automated license check 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. 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).
Does the OSS build phone home? Can I disable telemetry?
By default, Langfuse reports aggregated usage analytics (no personal data) so we know which features matter. No traces, prompts, or customer data leave your cluster. You can opt out of this.
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:
- Submit and vote on Ideas.
- Create and comment on Issues.
- Create a pull request. See Contributing.md to get started.
I want to see the code!
All our repositories are on GitHub:
- Langfuse Server (UI and API):
langfuse/langfuse - Langfuse Python SDK and integrations:
langfuse/langfuse-python - JS SDK and integrations:
langfuse/langfuse-js - Docs:
langfuse/langfuse-docs
Can you share some public metrics on how widely Langfuse is used?
Sure, we summarized some statistics in this blog post and in the dashboard below.