---
title: Langfuse Partners
description: Find a partner to build and improve production AI agents with Langfuse, or learn how your services firm can become delivery-ready.
---

# Partner with Langfuse

Help customers build, deploy, and continuously improve production AI agents. Langfuse is the open AI engineering platform that connects tracing, monitoring, prompt management, datasets, experiments, and evaluations in one workflow.

  <Button
    href="https://clickhouse.com/partners/become-partner"
    target="_blank"
    rel="noopener noreferrer"
    size="default"
  >
    Apply through House Mates
  </Button>
  <Button
    href="#become-delivery-ready"
    size="default"
    variant="secondary"
  >
    See the partner path
  </Button>

## One service motion for production AI

Langfuse fits into the AI implementation work your team already delivers. Partners can support the full customer journey from an initial agent implementation to the quality workflows and production handover that keep it reliable.

- **Build and instrument agents**: Implement agents and applications, then add Langfuse tracing and instrumentation so teams can understand behavior, cost, latency, and failure modes.
- **Establish quality workflows**: Define evaluation strategy, curate datasets, run experiments, monitor quality, and set up prompt-management workflows that customers can operate after handover.
- **Deploy Langfuse at scale**: Establish Langfuse as a platform across multiple development teams and introduce consistent AI development across the company.

This creates a broader services opportunity than platform delivery alone: help customers ship useful agents, make their behavior observable, establish a repeatable improvement loop, and transfer the system into production ownership.

## Why add Langfuse to your services portfolio?

- **Extend existing AI engagements.** Add observability, evaluation, experimentation, and prompt operations to agent and application delivery.
- **Give customers one connected improvement loop.** Teams can move from [traces](/docs/observability/overview) to monitoring, datasets, experiments, and evaluations without stitching together separate point tools.
- **Build reusable delivery assets.** Create reference implementations, evaluation templates, industry accelerators, and proof-of-concept patterns that shorten future projects.
- **Meet customers where they deploy.** Langfuse Cloud removes platform operations for the standard case, while the open-source platform can be [self-hosted](/self-hosting) for specific single-tenant requirements.

## Current Langfuse partner

GAO is the approved launch partner for this directory. More firms may be added after they demonstrate successful Langfuse delivery.

### [GAO](https://www.gao-ai.com/)

**Regions:** Japan, APAC

GAO helps organizations across Japan and APAC adopt Langfuse as part of production AI initiatives, with implementation services, technical support, and local procurement support in Japan.

**Capabilities:**

- AI agent implementation
- Langfuse professional services
- Technical support
- Local procurement in Japan

## Become delivery-ready [#become-delivery-ready]

This path is designed for systems integrators and professional services firms that already know how to build AI agents or AI-powered applications. It adds Langfuse product fluency and delivery evidence to that foundation.

<Steps>

### Confirm fit

Bring existing agent-development or AI-engineering experience and identify a named technical lead who will own Langfuse delivery readiness.

### Learn the “why”

Complete the [Langfuse Academy](/academy), with particular focus on the [AI engineering loop](/academy/ai-engineering-loop): Trace → Monitor → Datasets → Experiment → Evaluate.

### Learn the “how”

Work through the [product documentation](/docs) and [AI Engineering Library](/library). Use the [self-hosting documentation](/self-hosting) only when a customer requires that deployment model.

### Build hands-on

Complete the [Langfuse workshop](/workshop), then create a demonstrable agent implementation, reusable accelerator, or customer proof of concept that shows how you apply Langfuse in practice.

### Apply through House Mates

[Submit your House Mates application](https://clickhouse.com/partners/become-partner) with your AI delivery experience, geographic coverage, target customer segment, references, and delivery capabilities.

### Demonstrate delivery

Complete initial, well-scoped engagements with close Langfuse and ClickHouse collaboration. Partner recommendations and directory listing follow demonstrated delivery—not course completion alone.

</Steps>

  This is an enablement path, not a formal Langfuse certification. Completing the
  learning materials does not create an automatic endorsement, recommendation, or
  directory listing. Those follow demonstrated delivery capability and review.

## Grow through ClickHouse House Mates

Langfuse partner participation sits within the established [ClickHouse House Mates program](https://clickhouse.com/partners), rather than creating a separate partner program. Depending on program fit and participation, House Mates provides:

- Deal registration and protection
- Enablement resources and partner community access
- Field collaboration on qualified customer opportunities
- Joint go-to-market opportunities
- Visibility in the partner directory

## Commercial FAQ

<Details>
<Summary>What services can a Langfuse partner offer?</Summary>

Partners can package Langfuse implementation and advisory services into broader AI-agent engagements. Typical work includes agent implementation, tracing and instrumentation, evaluation design, datasets and experiments, quality monitoring, prompt-management workflows, and production handover.

</Details>

<Details>
<Summary>Does every engagement include platform deployment?</Summary>

No. Langfuse Cloud is the standard managed platform and does not require a partner-operated deployment. Platform delivery is an optional part of AI implementation, not a separate required service track.

</Details>

<Details>
<Summary>When does self-hosting apply?</Summary>

Partners may help with a single-tenant Langfuse deployment when a customer's security, compliance, or infrastructure requirements call for it. Start with Langfuse Cloud unless those requirements make self-hosting relevant.

</Details>

<Details>
<Summary>Can partners offer multi-tenant managed services or OEM Langfuse?</Summary>

Multi-tenant managed services and OEM arrangements require case-by-case review with Langfuse and ClickHouse before they are offered to customers.

</Details>

<Details>
<Summary>Do partners need deep ClickHouse expertise?</Summary>

Not for a standard Langfuse implementation on Langfuse Cloud. Deeper infrastructure and ClickHouse knowledge becomes relevant when supporting an advanced self-hosted deployment.

</Details>

## Ready to partner?

Bring your AI implementation experience, build hands-on Langfuse fluency, and show how your team can help customers run better production agents.

  <Button
    href="https://clickhouse.com/partners/become-partner"
    target="_blank"
    rel="noopener noreferrer"
    size="default"
  >
    Apply through House Mates
  </Button>
  <Button href="/academy" size="default" variant="secondary">
    Start with Langfuse Academy
  </Button>

<!-- agent-instructions -->

---

## 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/partners.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**: <https://langfuse.com/llms.txt>, 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 <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.