← Back to all projects

Phoenix
Tracing and evaluation that runs inside a notebook
OfficialSource-available
What is Phoenix?
Built on OpenTelemetry, so traces are portable rather than locked to one vendor, and it will run locally next to the code you are debugging. Licensed under Elastic 2.0 — fine for internal use, restrictive if you intend to offer it as a managed service.
What can you do with Phoenix?
- Instrument an app automatically —
npx @arizeai/phoenix-cli setup(orpx setuponce Phoenix is installed) detects your framework and LLM provider, installs the matching OpenInference instrumentation and wires up trace export. - Run the platform locally —
uvx arize-phoenix servebrings up the full platform with nothing installed, and the same build ships as a Docker Hub image and a Helm chart for cluster deployment. - Replay a captured LLM call — The Playground reruns a traced call with a different prompt, model or parameters, and prompt management keeps those changes under version control with tagging.
- Measure changes as experiments —
arize-phoenix-evalsscores response and retrieval quality against versioned datasets, so a prompt or retrieval change is compared as a tracked experiment rather than by eye. - Query traces from a coding agent — The remote MCP server built into Phoenix exposes a
/mcpendpoint that Claude Code, Cursor and other MCP clients can use to read traces, datasets and experiments.
Star history
15 Aug to 30 Oct · +1k
11.1k12.1k
Frequently asked questions
Is Phoenix free for commercial use?
Phoenix is published under Elastic-2.0, a source-available licence rather than OSI-approved open source — read its terms before relying on it commercially.
How can Phoenix be deployed?
Phoenix is available as Self-hosted / Runs locally / Managed cloud.