Phoenix
AI observability & evaluation: LLM tracing, evaluation, and RAG troubleshooting
Overview
Requirements
Recommended VPS
Contabo · VPS S
4 vCPU · 8192 MB · 100 GB
Contabo · VPS S
4 vCPU · 8192 MB · 100 GB
Contabo · VPS S
4 vCPU · 8192 MB · 100 GB
Affiliate disclosure
Docker Compose
# Generated by Run This Ai — docker-compose.yml
services:
phoenix:
image: arizephoenix/phoenix:latest
restart: unless-stopped
ports:
- 8080:8080
volumes:
- ./data/phoenix:/data
How to Install Phoenix using Docker Compose
Phoenix
Phoenix is an open-source AI observability platform designed for LLM tracing, evaluation, and RAG troubleshooting. It provides standard OpenTelemetry traces to monitor execution steps, calculate response metrics, and evaluate LLM output quality dynamically.
Prerequisites
- Docker installed (version 24.0+)
- Docker Compose (version 2.20+)
- At least 1GB RAM (2GB recommended)
Quick start with Docker
# Pull the image
docker pull arizephoenix/phoenix:latest
# Run the container
docker run -d --name phoenix -p 8080:8080 arizephoenix/phoenix:latestKey features
- Self-hosted and open source
- Docker-based deployment
- License: Apache-2.0
- Repository: https://github.com/Arize-AI/phoenix
- Docker image:
arizephoenix/phoenix:latest
Phoenix: Self-Hosted AI Observability & Evaluation Platform
Phoenix
Phoenix is an open-source AI observability platform designed for LLM tracing, evaluation, and RAG troubleshooting. It provides standard OpenTelemetry traces to monitor execution steps, calculate response metrics, and evaluate LLM output quality dynamically.
Key features
- Self-hosted and open source
- Docker-based deployment
- License: Apache-2.0
- Repository: https://github.com/Arize-AI/phoenix
- Docker image:
arizephoenix/phoenix:latest
What it's good for
Phoenix runs entirely on your own infrastructure — your data never leaves your server.
Related tools
Ollama
Run large language models locally
llama.cpp
LLM inference in C/C++
Open WebUI
User-friendly WebUI for LLMs (Ollama, OpenAI API)
SGLang
High-performance serving framework for LLMs with RadixAttention
Jan
Open-source ChatGPT replacement — run LLMs locally with full control and privacy
Llamafile
Distribute and run LLMs as single-file executables — no installation needed