Arize Phoenix vs Langfuse

Arize Phoenix is free, open-source software for tracing, evaluating, debugging, and improving AI applications. It captures model calls, retrieval, tool use, and custom logic as OpenTelemetry traces. Teams can score traces and spans with LLM evaluators, code checks, or human labels. Prompt tools provide versioning, side-by-side testing, and call replay, while dataset experiments compare evaluation results across application versions. Documented integrations include LlamaIndex, LangChain, DSPy, OpenAI, Bedrock, and Anthropic, plus evaluation libraries such as Harbor, Ragas, Cleanlab, and MLflow. Phoenix runs locally or can be self-hosted with Docker, Kubernetes, or a cloud environment; Arize says self-hosting keeps traces in the user’s environment. Self-hosted authentication supports OAuth2 identity providers with an OpenID Connect well-known endpoint. The Phoenix plan costs nothing and leaves trace spans, ingestion, projects, and retention under user management. The project is ELv2 licensed and built by Arize AI and the open-source community.

Langfuse is an open-source AI engineering platform for teams debugging, analyzing, and iterating on AI agent applications. Its tracing records prompts, model responses, token use, latency, tool calls, retrieval steps, and metadata. Prompt Management stores, versions, deploys, and tests prompts, then links them to traces. Evaluation features include LLM-as-a-judge, code evaluators, user feedback, manual labeling, datasets, and experiments. Integrations include Python and JS/TS SDKs, OpenTelemetry, an API, CLI, MCP Server, and popular AI frameworks. Teams can self-host the MIT-licensed core on customer infrastructure using Docker, with options including Docker Compose, Kubernetes, AWS, and Azure. Langfuse reports annual SOC 2 Type 2 and ISO 27001 audits, external penetration tests, GDPR compliance, a DPA, and a HIPAA-ready region. Its Cloud traffic uses TLS 1.2+ and stored data uses AES-256 encryption. The free Hobby plan is free and includes 50k units per month, 30 days of data access, two users, and community support via GitHub. Core costs $29 a month, billed monthly.