# Phoenix

> Open-source LLM tracing and evaluation.

Phoenix has a SharkScore of 65.3/100, ranked #60 of 673 in Frameworks & SDKs (updated 2026-11-19).

- Website: https://arize.com/phoenix/ (arize.com)
- Kind: Tool · Pricing: Open source
- Maker: Arize AI
- Repository: https://github.com/Arize-ai/phoenix
- Categories: Frameworks & SDKs
- Verified by the maker: no

## Why it scores 65.3

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 40 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Frameworks & SDKs.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | — |
| GitHub stars | 12.4K |
| Stars, last 90 days | — |
| Downloads, 30 days | 613.3K |
| Reviews | none yet |
| Last update | 0 days ago |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / yes / yes / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, Phoenix is an open-source tool for tracing and evaluating AI applications that can run locally or be self-hosted. [E1][E3]

Phoenix helps developers inspect AI application traces, evaluate outputs, iterate on prompts, and compare application changes using datasets and experiments. It is open source and can run locally or be self-hosted. [E1][E3]

### Pros

- Supports tracing, evaluations, prompt iteration, and experiments in one workflow.
- Offers local and self-hosted deployment options.
- The vendor describes Phoenix as built on OpenTelemetry and as working with any model, framework, or language.

### Cons

- The pages reviewed do not state a Phoenix-specific price or describe a managed Phoenix service.
- No public prices found on the pages we checked.
- No free plan or free trial stated on the pages we checked.

### Pricing

No public prices found on the pages we checked (2026-11-18).

### Sources

- https://arize.com/phoenix/ (fetched 2026-11-18)
- https://arize.com/pricing/ (fetched 2026-11-18)
- https://arize.com/docs/phoenix (fetched 2026-11-18)
- https://arize.com/privacy-policy/ (fetched 2026-11-18)
- https://arize.com/trust-center/ (fetched 2026-11-18)

## Top alternatives

1. [Model Context Protocol](https://rankshark.pro/tools/model-context-protocol) — SharkScore 81.7. Open protocol and SDKs that connect AI apps to tools and data.
2. [AI SDK](https://rankshark.pro/tools/ai-sdk) — SharkScore 77.7. TypeScript toolkit for building AI apps and agents.
3. [LangChain](https://rankshark.pro/tools/langchain) — SharkScore 77.7. Build agents and LLM apps in Python and TypeScript.
4. [LangSmith](https://rankshark.pro/tools/langsmith) — SharkScore 76.9. Tracing, evaluation and monitoring for LLM apps.
5. [Transformers](https://rankshark.pro/tools/transformers) — SharkScore 76.9. Hugging Face's library of pretrained models for text, vision and audio.

---
Source: https://rankshark.pro/tools/arize-phoenix · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
