# Phoenix

> AI observability and evaluation

Trace, evaluate and troubleshoot LLM apps and agents.

- Source: https://github.com/Arize-ai/phoenix
- Homepage: https://arize.com/docs/phoenix
- License: NOASSERTION
- Language: Python
- Stars: 11698
- Forks: 1180
- Contributors: 241
- Last commit: 2026-10-03
- Latest release: arize-phoenix-v20.19.0 (2026-10-01)
- Purpose: AI & LLM tooling, Evals & observability
- Runs on: Docker / self-host, Library / SDK
- For: Personal, Enterprise

## Worth score: 77/100

How much DigGitHub recommends it, from activity, adoption, docs, license and security signals.

- Popularity: 20/25
- Momentum: 10/20
- Maintenance: 25/25
- Community: 12/15
- Readiness: 10/15

## Alternatives

- [MLflow](https://diggithub.com/mlflow/mlflow.md): Open-source AI engineering platform
- [Opik](https://diggithub.com/comet-ml/opik.md): Debug, evaluate and monitor LLM apps
- [promptfoo](https://diggithub.com/promptfoo/promptfoo.md): Test and red-team LLM apps
- [Langfuse](https://diggithub.com/langfuse/langfuse.md): LLM engineering platform: tracing, evals and prompt management
- [Helicone](https://diggithub.com/Helicone/helicone.md): Open-source LLM observability
- [DeepEval](https://diggithub.com/confident-ai/deepeval.md): The LLM evaluation framework

---

Source page: https://diggithub.com/Arize-ai/phoenix
Updated: 2026-10-04