Phoenix vs MLflow
Two of the top observability, side by side: score, setup, license, activity and what each review found.
Phoenix
LLM tracing, evals, datasets and prompt playground built on OpenTelemetry
MLflow
Tracing, evals, prompt registry and AI gateway plus classic ML tracking
| What we compare | Phoenix | MLflow |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 52, popular | 75, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 79, fair | 87, healthy |
| Easy to run | 67, easy | 33, some setup |
| Agent-ready | 85, ready | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 11.8k | 28.3k |
| License | custom license (read the license) | Apache-2.0 (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Python | Not stated |
| Docker | Yes | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
Phoenix
Phoenix collects traces from LLM applications through OpenTelemetry/OpenInference instrumentation and shows them in a web UI. It also covers LLM-based evals, versioned datasets, experiments, prompt management and a prompt playground that can replay traced calls. It runs via pip, uvx, Docker or a Helm chart, and exposes a remote MCP endpoint at /mcp for coding agents.
Who it is for: Teams debugging and evaluating LLM apps who want self-hosted tracing
Strengths
- Install with pip or uvx and run `phoenix serve`; no separate setup shown
- Auto-instrumentation for LangGraph, LlamaIndex, CrewAI, DSPy, Vercel AI SDK and more
- Built-in MCP server at /mcp lets Claude Code and Cursor query traces
- Python and TypeScript packages for OTel, client and evals
Weaknesses
- License reported as NOASSERTION; terms need checking before commercial use
- Managed production workflows are pushed to the paid Arize AX product
- Azure template serves plain HTTP and needs a TLS proxy in front
- RAM, storage backend and default port not stated in the README excerpt
- no GPU
- Docker + Compose
- Compose runs PostgreSQL
- Models: OpenAI, Anthropic, Google GenAI, AWS Bedrock, OpenRouter
MLflow
Single mlflow server (port 5000) that records OpenTelemetry traces from 60+ frameworks via one-line autolog, runs evaluations with 50+ metrics and LLM judges, versions and optimizes prompts, and fronts providers through an OpenAI-compatible AI Gateway with rate limits, fallbacks and traffic splitting. Keeps the original experiment tracking, model registry and deployment tooling. For teams wanting one platform for GenAI and ML.
Who it is for: Teams wanting one platform for GenAI tracing and ML tracking
Strengths
- One-line autolog for 60+ frameworks in Python, TypeScript and Java; MCP and OTel native
- Starts with uvx mlflow server; no separate database needed to begin
- AI Gateway adds credential management, guardrails and A/B traffic splitting
- Setup wizard lets Claude Code, Codex or OpenCode add tracing to a project
Weaknesses
- README covers the quickstart; production backend store and auth setup live in docs
- Broad scope (ML tracking plus GenAI) means a large install and UI surface
- No Dockerfile or compose file at the repo root
- TypeScript and Java coverage is smaller than Python (5 TS and 2 Java frameworks listed)
- no GPU
- Docker + Compose
- Models: any LLM provider via autolog or the AI Gateway
- port 5000