Developer Frameworks & Infrastructure
Langfuse
Open-source LLM observability, prompt management, and evaluation
Open sourceRuns on your device
GitHub stars
37.1K
37,139 stars
Community forks
4.2K
Open collaboration
License
Other
Read the full license
Platforms
macOS - Windows - Linux
Also Web
Last activity
Nov 8
Repository push date
Best for
Agent trajectory debugging
Trace nested multi-step tool calls and inspect exact input and output payloads.
Pricing checked Oct 2026
User feedback
No aggregate rating verified
Explore discussions, issues, and documentation to see how this project fits your workflow.
GitHub stars measure repository interest, not customer satisfaction.
Read Prother reviews (0) - write your ownHide Prother reviews
Reviews (0)
HONEST AND VERIFIED ONLYReview Langfuse
Share real experiences on ease of use, feature power, and overall value.
About Langfuse
Langfuse is an open-source observability and analytics platform purpose-built for LLM applications. It instruments the entire lifecycle of generative AI features, capturing nested traces of agent tool calls, retrieval steps, model latencies, and token consumption.
The platform integrates prompt management with visual version history and SDK-driven dynamic parameter injection, eliminating the risk of unversioned prompt edits in production. Its evaluation framework supports human-in-the-loop annotation, user feedback collection (thumbs up/down), and model-based scoring pipelines. With native integrations for LangChain, LlamaIndex, LiteLLM, and raw OpenAI SDKs, Langfuse provides teams with visibility into where agent loops fail, costs spike, or hallucinated responses occur.
- Permissive MIT license with complete self-hosting Docker compose support
- Low-latency asynchronous telemetry that never blocks user requests
- Comprehensive SDKs for Python, TypeScript, and popular AI frameworks
- Built-in prompt management and scoring dashboards
- Self-hosting requires Postgres, ClickHouse, and worker infrastructure
- Setup requires deliberate telemetry instrumentation across your codebase
git clone https://github.com/langfuse/langfuse.gitOpen source tool available on GitHub.
Alternative to Langfuse
Compare in matrix →These tools share use cases. Features, costs, and deployment needs differ.
Practical Guides & In-Depth Evaluations
More in Developer Frameworks & Infrastructure
See categoryThe layer builders stand on: training frameworks, model hubs, agent orchestration, vector databases, and pay-per-second inference APIs. Repository health, license clarity, and self-hosting paths are part of every listing so teams can evaluate lock-in at a glance.
