Home / Directory / AI SaaS tooling / Observability & monitoring / Langfuse
Langfuse
Open-source LLM engineering platform for observability, prompt management, evaluations, and metrics, with cloud and self-host options.
AI engineering teams that want LLM tracing, prompt management, and evals with the option to self-host.
Buyers who only want a closed SaaS with no open-source path, or teams with no LLM applications.
Verdict
Langfuse is an open-source LLM engineering platform founded by Marc Klingen, Max Deichmann, and Clemens Rawert. It covers tracing, prompt management, evaluation, and metrics, with cloud and self-hosting options and a Y Combinator background. It matters because LLM apps fail quietly in production without traces and evals, and Langfuse gives teams an open stack they can run themselves or buy hosted.
Score Breakdown
How Langfuse scores in the categories that matter to its buyers.
Pricing
Langfuse offers open-source self-hosting plus a commercial cloud. Exact cloud tiers are listed in-product and docs rather than a single marketing price card.
Self-host the open-source stack for free, or use Langfuse cloud. Teams pick based on data residency and support needs.
The Field at a Glance
How Langfuse compares with other Observability & monitoring vendors we reviewed, by Overall Score and relative typical engagement cost.
Langfuse scores 7.9 in Observability & monitoring, under Fiddler AI (8.1), level with Raindrop (7.9), and ahead of Arize AI (7.7) and Evidently AI (6.8). Relative cost lands lower for this subcategory.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Production LLM observability | Strong | Tracing is the entry point in docs and product. |
| Prompt management | Strong | First-class product pillar. |
| Evaluations | Strong | Eval platform is marketed alongside tracing. |
| Self-hosting | Strong | Explicit self-host docs path. |
| Non-LLM APM | Weak | Built for LLM apps. |
| No-ops fully managed only | Mixed | Cloud exists; open-source expects ops ownership. |
Who it’s for
Good fit
- AI startups and platform teams
- Companies that must self-host
- Teams standardizing on open LLM tooling
Poor fit
- Teams without LLM apps
- Buyers refusing open-source ops
- Non-technical orgs needing only a dashboard
Review Excerpts
Below are excerpts from public reviews. Our team scoured public reviews, forums, and chat rooms to get a balanced view of customers' experience with this company. Paid reviews and pay-for-play sites such as Clutch were excluded.
Langfuse describes itself as an open-source agent evals and observability platform covering LLM observability, prompt management, evaluation, and metrics, with get-started tracing guides for OpenAI and LangChain.
The About page identifies co-founders Marc Klingen, Max Deichmann, and Clemens Rawert and frames Langfuse as an open-source LLM engineering platform with cloud and self-host options.
Self-hosting gives control but shifts operations onto your team, so groups without platform engineers may prefer a fully managed vendor and should budget for that ownership.
Company Facts
- Founded
- 2022 (CB Insights)
- Headquarters
- Berlin, Germany (CB Insights)
- Employees
- About 26 (Y Combinator)
- Total funding raised
- $4.5M (CB Insights)
- Status
- Acquired by ClickHouse in January 2026 (CB Insights, Langfuse)
- Key investors
- ClickHouse, Y Combinator, Lightspeed, La Famiglia (CB Insights)
- Accelerator
- Y Combinator, Winter 2023 batch (Y Combinator)
- Website
- langfuse.com
Key Leadership
Marc Klingen
Co-founder and CEO
Methodology
This page is an independent evaluation of Langfuse for buyers comparing options in observability & monitoring. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Langfuse did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria sit under it in two groups.
- Buyer outcomes (for observability & monitoring)
- Open-source LLM tracing
- Prompt management
- Evals and metrics
- Turnkey enterprise support packaging
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Langfuse is graded here as observability & monitoring. Criteria scores can move as more review volume and product checks are added.