# Arize-ai/phoenix

AI Observability & Evaluation

Repository: https://github.com/Arize-ai/phoenix
Canonical: https://ross.abutalabs.com/products/arize-ai-phoenix
Homepage: https://arize.com/docs/phoenix
Language: Python
License: NOASSERTION
License Family: other
Topics: llmops, ai-monitoring, ai-observability, llm-eval, aiengineering, datasets, agents, llms, prompt-engineering, anthropic, evals, llm-evaluation, openai, langchain, llamaindex, smolagents
Last push: 2026-08-27T00:10:14+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 99
- inputs: {"age_days": 1393, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 557}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11205, forks 1080 (observed 2026-08-28T04:10:46.414996+00:00)

## What it is
Arize Phoenix is an open-source AI observability and evaluation platform for tracing, debugging, and evaluating LLM applications. It supports OpenTelemetry-based tracing, LLM-as-a-judge evals, prompt iteration, datasets, and experiments, and can be self-hosted for free.

## Use cases
- trace and debug LLM application runs
- evaluate LLM outputs with LLM-as-a-judge
- catch regressions in AI app quality
- iterate on prompts using production examples
- run experiments comparing prompt or model changes
- self-host AI observability with data staying on-prem
- instrument LangChain or LlamaIndex apps with OpenTelemetry

## When to choose
- you need end-to-end tracing for LLM apps built with LangChain, LlamaIndex, OpenAI, or Anthropic
- you want free, fully-featured self-hosted LLM observability with no data leaving your infrastructure
- you need systematic evaluation of RAG or agent outputs including LLM-as-a-judge scoring
- you want to compare prompt and model changes with datasets and experiments

## When to avoid
- you only need simple application performance monitoring without LLM-specific features
- you want a fully managed enterprise observability platform with vendor support (consider Arize AX)
- your stack has no LLM or AI components

## Facets
- artifact type: application
- maturity: active
- function: monitoring, tracing, llm-inference, rag, prompt-engineering, agent-framework, benchmarking
- domain: large-language-models, monitoring, developer-tools, machine-learning
- platform: python, self-hosted, cli
- tags: llmops, opentelemetry, llm-evaluation, llm-as-a-judge, openinference, prompt-management, experiments, tracing, ai-agents, docker, kubernetes, web-server

## Member repositories
- Arize-ai/phoenix (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.414996+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:16:27.499625+00:00, confidence not recorded.
  - readme: https://github.com/Arize-ai/phoenix (fetched 2026-08-28T04:10:46.414996+00:00, sha 5b557a149e55)
  - homepage: https://arize.com/docs/phoenix (fetched 2026-08-29T08:15:12.804366+00:00, sha 5bc5f0189157)
  - site_page: https://arize.com/docs/phoenix/integrations (fetched 2026-08-29T08:15:12.810025+00:00, sha e163847d2dc0)
  - site_page: https://arize.com/docs/phoenix/sdk-api-reference (fetched 2026-08-29T08:15:12.812698+00:00, sha edb810701b5a)
  - site_page: https://arize.com/docs/phoenix/self-hosting (fetched 2026-08-29T08:15:12.814934+00:00, sha d02fe3e2d845)
  - site_page: https://arize.com/docs/phoenix/cookbook (fetched 2026-08-29T08:15:12.816776+00:00, sha 65fe4d300334)
  - site_page: https://arize.com/docs/phoenix/release-notes (fetched 2026-08-29T08:15:12.818517+00:00, sha 96077c5d09a6)
  - site_page: https://arize.com/docs/phoenix/pxi (fetched 2026-08-29T08:15:12.820107+00:00, sha 31bd6706d3a9)
  - site_page: https://arize.com/docs/phoenix/evaluation/llm-evals (fetched 2026-08-29T08:15:12.822333+00:00, sha cf926b325ee5)
  - site_page: https://arize.com/docs/phoenix/evaluation/concepts-evals/llm-as-a-judge (fetched 2026-08-29T08:15:12.824100+00:00, sha b50200095865)
- Data as of 2026-08-30T08:39:29.467469+00:00.