🪢 Langfuse
Open Source Observability & Analytics for LLM Apps 🕵️♂️
SubscriptionOpen SourceMonitoringAI69,876 impressions#2 of its week8 comments
Comments
>log in to comment- Mika Sagindyk· 3y ago
Congrats!
- David Paffenholz· 3y ago
Big fans of Langfuse since Day 1!
- Gyri Reiersen· 3y ago
🔥🔥
- B. Assadsolimani· 3y ago
Let’s go!
- Collin Schneider· 3y ago
Love this! Working with LLMs have always felt so daunting to due it being a black box in nature, building with Langfuse makes building AI applications so much less scary.
- Raphael Kaiser· 3y ago
Stellar team building a stellar product. Congrats on the Launch!
- Niklas Hölterhoff· 3y ago
Amazing tooling, excited to see what's next! 🚀🚀🚀
Langfuse is an open-source platform for tracing, evaluating and monitoring LLM applications and AI agents.
- for
- Developers building, debugging and scaling LLM-based apps and agents.
- pricing
- freemium
- license
- open source
Key features
- Hierarchical Traces — Capture every LLM call, tool invocation and retrieval step with filters for user, session, cost and latency.
- Prompt Management — Version, fetch, release and cache prompts separately from code with one-click deployments.
- Evaluation Engine — Run LLM-as-judge, heuristic or human-review evaluations on production data or experiments.
- Experiments & Datasets — Define test cases, run experiments and create golden datasets for continuous improvement.
- Dashboards & Alerts — Monitor cost, latency and quality via custom dashboards and automated alerts.
- Human Annotation — Collaborative human-in-the-loop workflows with annotation queues.
- Extensive Integrations — Supports Python, TypeScript, Go, Java, .NET, Ruby, PHP, Swift and 100+ agent frameworks and model providers.
- Self-hosted & Cloud Options — Available as hosted SaaS or self-hosted under MIT license.
Use cases
- Debugging LLM response latency and cost in production
- Running A/B experiments on prompt variations
- Creating evaluation datasets from real user interactions
- Collaborating on human annotation for model fine-tuning
- Monitoring AI agents across multiple tool invocations
Langfuse pricing
- HobbyFree50k units / month · 30 days data access · 2 users · Community support
- Core$29/month100k units / month · 90 days data access · Unlimited users · In-app support
- Pro$199/monthUnlimited history · 3 years data access · SOC2 & ISO27001 reports · Prioritized support
- Enterprise$2499/monthCustom volume pricing · Audit logs · Uptime SLA · Dedicated support engineer
Langfuse vs alternatives
| Best for | LLM observability & analytics | General system observability | Cloud infrastructure monitoring | Website analytics | CI/CD pipeline scripting |
|---|---|---|---|---|---|
| Pricing | Freemium | Subscription | Free | Subscription | Free |
| DevHunt upvotes | 89 | 39 | 39 | 111 | 158 |
| Launched | Jan 2023 | Apr 2026 | Feb 2024 | Jan 2023 | Jan 2024 |
- Langfuse vs OpenObserve: OpenObserve focuses on petabyte-scale system metrics, not LLM-specific tracing and evaluation.
- Langfuse vs groundcover: Groundcover provides cloud-native observability but lacks built-in LLM prompt management and evaluation features.
- Langfuse vs Overtracking Analytics: Overtracking Analytics is a web analytics tool, not tailored for LLM app tracing or agent evaluation.
- Langfuse vs Fluent CI: Fluent CI automates CI/CD pipelines, unrelated to LLM observability.
Langfuse FAQ
Is there a free tier?+
Yes, the Hobby plan is free with no credit card required and includes 50k units per month.
Can I self-host Langfuse?+
Yes, Langfuse is MIT-licensed open source and can be self-hosted.
What data retention is available on each plan?+
Hobby provides 30 days, Core 90 days, Pro 3 years, and Enterprise offers custom retention.
How are usage costs billed beyond the included units?+
Additional usage is $8 per 100k units for Core, Pro and Enterprise, with volume discounts.
What support options exist?+
Community GitHub support is free; Core and higher plans get in-app support, and Enterprise adds dedicated Slack/MS Teams channels and SLA guarantees.
Summarized by DevHunt from langfuse.com · Sep 27, 2026. Details may change; check the official site.