Arize Phoenix
Open-source AI observability and evaluation platform
Phoenix by Arize is an open-source observability platform for experimentation, evaluation and troubleshooting of LLM and ML applications. It runs as a self-hosted server collecting OpenTelemetry traces from AI apps.
Key features
- LLM tracing and spans
- Built-in evaluators
- OpenTelemetry-based
- Self-hostable
Strengths
- Released under the Elastic-2.0 license
- First-class Docker support for quick deployment
- Mature project with 10.9k GitHub stars
- Written in Python
Arize Phoenix replaces
Compare Arize Phoenix
18 head-to-head comparisons.
- Arize Phoenix vs OpenClaw
- Arize Phoenix vs Hermes Agent
- Arize Phoenix vs OpenCode
- Arize Phoenix vs Hugging Face Transformers
- Arize Phoenix vs Langflow
- Arize Phoenix vs Dify
- Arize Phoenix vs PaddleOCR
- Arize Phoenix vs RAGFlow
- Arize Phoenix vs OpenHands
- Arize Phoenix vs screenshot-to-code
- Arize Phoenix vs Langfuse
- Arize Phoenix vs promptfoo
- Arize Phoenix vs DeepEval
- Arize Phoenix vs Ragas
- Arize Phoenix vs Prompt flow
- Arize Phoenix vs OpenLLMetry
- Arize Phoenix vs Agenta
- Arize Phoenix vs Weave
Similar self-hosted ai apps
OpenClaw
Self-Hosted AIThe AI that actually does things
Hermes Agent
Self-Hosted AIThe AI agent that grows with you
OpenCode
Self-Hosted AIThe open source AI coding agent
Hugging Face Transformers
Self-Hosted AIState-of-the-art machine learning model library
Replaces OpenAI API
Langflow
Self-Hosted AIVisual framework for building AI agents and RAG pipelines
Replaces Vertex AI Agent Builder
Dify
Self-Hosted AIOpen-source platform for building production LLM apps
Replaces OpenAI Assistants, Vertex AI Agent Builder