Hobbyper month
$0/month
- 50k units/month included
Finding your next stop…
Loading the latest directory information.
Loading the latest directory information.
Start here for the decision-making essentials: what Langfuse does, who it is for, how it is accessed, and the first-party sources behind this profile.
$0/month
Langfuse is an open-source AI engineering platform under MIT license that helps teams trace, evaluate, and improve LLM applications and AI agents. It offers hierarchical tracing, prompt management, LLM-as-a-judge evaluation, and 100+ integrations, deployable as cloud or self-hosted.
Read-only public captures of Langfuse’s homepage. Screenshots are dated, never live embeds, and open full-screen.
Short answers to the questions buyers and builders commonly ask about Langfuse. Each answer cites the shared ledger below, where every source is listed once.
Unified platform for tracing, prompt management, evaluation, and experiments across the LL · Production tracing, metrics, and analytics for LLM applications · Version control and deployment of prompts with integrated monitoring · LLM-as-a-Judge evaluations, datasets, and structured evaluation processes
One integrated platform to trace, manage prompts, evaluate, and experiment from prototype to production scale.
Trace, evaluate, and improve AI agents using production data to debug traces, optimize spe · Building LLM applications · Understanding, evaluating, and improving AI agents
Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
Tracing adds no application latency (SDKs send traces asynchronously in batches) · Tool-type observations can only be opened in the playground when they are in the OpenAI Ch
Langfuse SDKs send tracing data asynchronously in the background. Trace events are queued locally and flushed in batches, so your application's response time is not affected.
Core | $0 base subscription | 100k units/month included, additional usage at $8/100k units · Enterprise | Custom Volume Pricing | Audit Logs, SCIM API, custom rate limits, uptime SLA,
Everything in Core - 100k units / month included, additional: $8/100k units. Lower with volume (pricing calculator) - 3 years data access - Data retention management - Unlimited annotation queues - High rate limits
API-first architecture with public API for custom integrations and data exports to blob st · All features are available via API for custom integrations · Observations API v2 with cursor-based pagination and Metrics API v2 aggregating cost, toke · Public API for prompts (creation, versioning, runtime fetch, bulk migrations, CI/CD)
API-first architecture - Data exports to blob storage - Enterprise security and administration
100+ library and framework integrations across models and stacks · Model and framework agnostic with 100+ integrations · OpenAI, LangChain, and first-party SDKs for trace ingestion · Monitor notifications delivered via Slack, webhooks, or GitHub Actions
100+ integrations make getting started even easier.
This profile connects the jobs Langfuse is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
HTTP 200 verified twice
Langfuse
Open source (MIT) with public API for custom integrations · Unified platform for tracing, prompt management, evaluation, and experiments · Works with any language and framework via OpenTelemetry instrumentation
Yes — open source, self-hostable, with public API for custom integrations
Unified platform for tracing, prompt management, evaluation, and experiments across the LLM application lifecycle
Trace, evaluate, and improve AI agents using production data to debug traces, optimize spend, and build evals
Works with any language and framework via OpenTelemetry instrumentation, plus native Python and JavaScript SDKs
100+ library and framework integrations across models and stacks
Self-hostable (free) or managed cloud with ClickHouse backend for querying millions of traces in milliseconds
OpenTelemetry-native standard trace format
API-first architecture with public API for custom integrations and data exports to blob storage
SOC2 and ISO27001 reports, HIPAA-ready region, Enterprise SSO, SSO enforcement, fine-grained RBAC, audit logs, and SCIM API available on higher tiers
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Self-hosted users can now configure multiple Langfuse deployments and switch between them from the sidebar user menu, mirroring the Cloud region switcher.
View source [21]Added a compact chart strip above the Observations table visualizing count, cost, and latency spikes over time; clicking or dragging a bar narrows the table to that window.
View source [20]Toggle the Observations table into a chart using the same query and filters, with chart type, metric, aggregation, and breakdown options, then add it to a dashboard.
View source [19]Experiments now live as a top-level feature alongside Datasets, runnable with or without datasets, with cross-run comparisons and progress tracking.
View source [1]A new TEXT score type was added to capture open-ended feedback and qualitative annotations.
View source [1]Langfuse now delivers faster product performance at scale, with rollout, access, and migration steps documented on an overview page.
View source [1]Adds day 1 support for OpenAI GPT-5.2 across all major Langfuse features.
View source [1]Langfuse now supports OpenAI GPT-5.2 with day 1 support across all major features.
View source [1]Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.
These tools share a workflow, capability or audience with Langfuse. They may complement it rather than replace it, and are not presented as integrations or endorsements.
Core | $0 base subscription | 100k units/month included, additional usage at $8/100k units, 3 years data access, unlimited annotation queues, high rate limits
Enterprise | Custom Volume Pricing | Audit Logs, SCIM API, custom rate limits, uptime SLA, support SLA, dedicated support engineer, architecture reviews, billing via AWS Marketplace or invoice, vendor onboarding
Production tracing, metrics, and analytics for LLM applications
Version control and deployment of prompts with integrated monitoring
LLM-as-a-Judge evaluations, datasets, and structured evaluation processes
Shareable views, custom dashboards, and team collaboration features
MIT
Available as cloud or self-hosted at production scale
Model and framework agnostic with 100+ integrations
All features are available via API for custom integrations
Part of ClickHouse, Inc. (ClickHouse acquired Langfuse in January 2026)
2023
Berlin, Germany (Product & Engineering) and San Francisco, CA (GTM)
16+ full-time employees
LLM Observability
Prompt Management
Evaluation with model-based (LLM-as-a-Judge), human annotations, and custom evaluation workflows via API/SDKs
Building LLM applications
Available as Langfuse Cloud and generally available for self-hosted deployments
Langfuse has joined ClickHouse
Demo apps are fully open source
OpenAI, LangChain, and first-party SDKs for trace ingestion
Monitor notifications delivered via Slack, webhooks, or GitHub Actions
Observations API v2 with cursor-based pagination and Metrics API v2 aggregating cost, tokens, volume, latency, and scores
Langfuse Assistant for plain-language queries over traces, observations, sessions, and metrics
In-app support form and GitHub Discussion for rollout and migration questions
Open source
Application tracing and observability for LLM apps (traces, latency, costs, token usage, prompts, responses, tool/retrieval steps)
Adds observation-level LLM-as-a-Judge evaluations for precise operation-specific scoring in production monitoring.
View source [1]Enables fetching datasets at specific version timestamps and running experiments on historical dataset versions via UI, API, and SDKs for full reproducibility.
View source [1]Allows capturing improved versions of LLM outputs directly in trace views to build fine-tuning datasets and drive continuous improvement with domain expert feedback.
View source [1]Adds the ability to anchor comments to specific text selections within trace and observation input, output, and metadata fields.
View source [1]Adds filtering, table columns, and dashboard widgets for analyzing tool usage in LLM applications.
View source [1]Introduced new high-performance v2 APIs for metrics and observations with cursor-based pagination, selective field retrieval, and optimized data architecture.
View source [1]Langfuse introduced v2 metrics and observations, updating its core data model used for trace analytics.
View source [1]Introduces new high-performance v2 APIs for metrics and observations with cursor-based pagination, selective field retrieval, and optimized data architecture.
View source [1]Track dataset changes over time with automatic versioning on every addition, update, or deletion of dataset items.
View source [1]Track dataset changes over time with automatic versioning on every addition, update, or deletion of dataset items.
View source [1]Select multiple observations from the observations table and add them to a new dataset in bulk.
View source [1]
