freshcrate
Skin:/
Language:English/įŽ€äŊ“中文
Home > Testing > phoenix

phoenix

AI Observability & Evaluation

agentsai-monitoringai-observabilityaiengineeringanthropicdatasetsevalsjupyter notebooklangchainprompt-engineering
Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

AI Observability & Evaluation

README

phoenix banner

Add Arize Phoenix MCP server to Cursor

Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:

  • Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
  • Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
  • Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
  • Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
  • Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
  • Prompt Management- Manage and test prompt changes systematically using version control, tagging, and experimentation.

Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (OpenAI Agents SDK, Claude Agent SDK, LangGraph, Vercel AI SDK, Mastra, CrewAI, LlamaIndex, DSPy) and LLM providers (OpenAI, Anthropic, Google GenAI, Google ADK, AWS Bedrock, OpenRouter, LiteLLM, and more). For details on auto-instrumentation, check out the OpenInference project.

Phoenix runs practically anywhere, including your local machine, a Jupyter notebook, a containerized deployment, or in the cloud.

Installation

Install Phoenix via pip or conda

pip install arize-phoenix

Phoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes. Arize AI also provides cloud instances at app.phoenix.arize.com.

Packages

The arize-phoenix package includes the entire Phoenix platform. However, if you have deployed the Phoenix platform, there are lightweight Python sub-packages and TypeScript packages that can be used in conjunction with the platform.

Python Subpackages

Package Version & Docs Description
arize-phoenix-otel PyPI Version Docs Provides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults
arize-phoenix-client PyPI Version Docs Lightweight client for interacting with the Phoenix server via its OpenAPI REST interface
arize-phoenix-evals PyPI Version Docs Tooling to evaluate LLM applications including RAG relevance, answer relevance, and more

TypeScript Subpackages

Package Version & Docs Description
@arizeai/phoenix-otel NPM Version Docs Provides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults
@arizeai/phoenix-client NPM Version Docs Client for the Arize Phoenix API
@arizeai/phoenix-evals NPM Version Docs TypeScript evaluation library for LLM applications (alpha release)
@arizeai/phoenix-mcp NPM Version Docs MCP server implementation for Arize Phoenix providing unified interface to Phoenix's capabilities
@arizeai/phoenix-cli NPM Version Docs CLI for fetching traces, datasets, and experiments for use with Claude Code, Cursor, and other coding agents

Tracing Integrations

Phoenix is built on top of OpenTelemetry and is vendor, language, and framework agnostic. For details about tracing integrations and example applications, see the OpenInference project.

Python Integrations

Integration Package Version
OpenAI openinference-instrumentation-openai PyPI Version
OpenAI Agents openinference-instrumentation-openai-agents PyPI Version
LlamaIndex openinference-instrumentation-llama-index PyPI Version
DSPy openinference-instrumentation-dspy PyPI Version
AWS Bedrock openinference-instrumentation-bedrock PyPI Version
LangChain openinference-instrumentation-langchain PyPI Version
MistralAI openinference-instrumentation-mistralai PyPI Version
Google GenAI openinference-instrumentation-google-genai PyPI Version
Google ADK openinference-instrumentation-google-adk PyPI Version
Guardrails openinference-instrumentation-guardrails PyPI Version
VertexAI openinference-instrumentation-vertexai PyPI Version
CrewAI openinference-instrumentation-crewai PyPI Version
Haystack openinference-instrumentation-haystack PyPI Version
LiteLLM openinference-instrumentation-litellm PyPI Version
Groq openinference-instrumentation-groq PyPI Version
Instructor openinference-instrumentation-instructor PyPI Version
Anthropic openinference-instrumentation-anthropic PyPI Version
Smolagents openinference-instrumentation-smolagents PyPI Version
Agno openinference-instrumentation-agno PyPI Version
MCP openinference-instrumentation-mcp PyPI Version
Pydantic AI openinference-instrumentation-pydantic-ai PyPI Version
Autogen AgentChat openinference-instrumentation-autogen-agentchat PyPI Version
Portkey openinference-instrumentation-portkey PyPI Version
Agent Spec openinference-instrumentation-agentspec PyPI Version
Claude Agent SDK openinference-instrumentation-claude-agent-sdk PyPI Version

Span Processors

Normalize and convert data across other instrumentation libraries by adding span processors that unify data.

Package Description Version
openinference-instrumentation-openlit OpenInference Span Processor for OpenLIT traces. PyPI Version
openinference-instrumentation-openllmetry OpenInference Span Processor for OpenLLMetry (Traceloop) traces. PyPI Version

JavaScript Integrations

Integration Package Version
OpenAI @arizeai/openinference-instrumentation-openai NPM Version
LangChain.js @arizeai/openinference-instrumentation-langchain NPM Version
Vercel AI SDK @arizeai/openinference-vercel NPM Version
BeeAI @arizeai/openinference-instrumentation-beeai NPM Version
Claude Agent SDK @arizeai/openinference-instrumentation-claude-agent-sdk NPM Version
Mastra @mastra/arize NPM Version
MCP @arizeai/openinference-instrumentation-mcp NPM Version

Java Integrations

Integration Package Version
LangChain4j openinference-instrumentation-langchain4j Maven Central
SpringAI openinference-instrumentation-springAI Maven Central
Arconia openinference-instrumentation-springAI Maven Central

Platforms

Platform Description Docs
BeeAI AI agent framework with built-in observability Integration Guide
Dify Open-source LLM app development platform Integration Guide
Envoy AI Gateway AI Gateway built on Envoy Proxy for AI workloads Integration Guide
LangFlow Visual framework for building multi-agent and RAG applications Integration Guide
LiteLLM Proxy Proxy server for LLMs Integration Guide
Flowise Visual framework for building LLM applications Integration Guide
Prompt Flow Microsoft's prompt flow orchestration tool Integration Guide
NVIDIA NeMo NVIDIA NeMo Agent Toolkit for enterprise agents Integration Guide
Graphite Multi-agent LLM workflow framework with visual builder Integration Guide

Coding Agent Skills

This repository includes skills that teach coding agents how to work with Phoenix. They are located in .agents/skills/ and can be used with Claude Code, Cursor, and other compatible tools.

Skill Description
phoenix-cli Debug LLM applications using the Phoenix CLI — fetch traces, analyze errors, review experiments, and query the GraphQL API
phoenix-evals Build and run evaluators for AI/LLM applications using Phoenix
phoenix-tracing OpenInference semantic conventions and instrumentation for tracing LLM applications

Security & Privacy

We take data security and privacy very seriously. For more details, see our Security and Privacy documentation.

Telemetry

By default, Phoenix collects basic web analytics (e.g., page views, UI interactions) to help us understand how Phoenix is used and improve the product. None of your trace data, evaluation results, or any sensitive information is ever collected.

You can opt-out of telemetry by setting the environment variable: PHOENIX_TELEMETRY_ENABLED=false

Community

Join our community to connect with thousands of AI builders.

  • 🌍 Join our Slack community.
  • 📚 Read our documentation.
  • 💡 Ask questions and provide feedback in the #phoenix-support channel.
  • 🌟 Leave a star on our GitHub.
  • 🐞 Report bugs with GitHub Issues.
  • 𝕏 Follow us on 𝕏.
  • đŸ—ēī¸ Check out our roadmap to see where we're heading next.
  • 🧑‍đŸĢ Deep dive into everything Agents and LLM Evaluations on Arize's Learning Hubs.

Breaking Changes

See the migration guide for a list of breaking changes.

Copyright, Patent, and License

Copyright 2025 Arize AI, Inc. All Rights Reserved.

Portions of this code are patent protected by one or more U.S. Patents. See the IP_NOTICE.

This software is licensed under the terms of the Elastic License 2.0 (ELv2). See LICENSE.

Release History

VersionChangesUrgencyDate
arize-phoenix-v17.1.0## [17.1.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v17.0.0...arize-phoenix-v17.1.0) (2026-06-02) ### Features * **playground:** add PXI load_dataset tool ([#13558](https://github.com/Arize-ai/phoenix/issues/13558)) ([96678ef](https://github.com/Arize-ai/phoenix/commit/96678efd16ec9675e048caceba1308b6ed138e2e)) * **pxi:** LLM-evaluator authoring for the PXI agent ([#13579](https://github.com/Arize-ai/phoenix/issues/13579)) ([1ead013](https://github.com/Arize-ai/phoenix/commiHigh6/2/2026
arize-phoenix-v16.3.0## [16.3.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v16.2.0...arize-phoenix-v16.3.0) (2026-05-27) ### Features * Add drag-to-zoom for project metric charts ([#13434](https://github.com/Arize-ai/phoenix/issues/13434)) ([4fe68f8](https://github.com/Arize-ai/phoenix/commit/4fe68f8e060ea250ad56e065ba5acbd69854cba3)) * **agents:** add skills capability to PXI agent ([#13349](https://github.com/Arize-ai/phoenix/issues/13349)) ([5ef9729](https://github.com/Arize-ai/phoenix/commit/5High5/27/2026
arize-phoenix-v16.0.0## [16.0.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v15.12.0...arize-phoenix-v16.0.0) (2026-05-21) [MIGRATION.md](https://github.com/Arize-ai/phoenix/blob/main/MIGRATION.md) ### ⚠ BREAKING CHANGES * Sandboxing and Code Evaluators ([#13290](https://github.com/Arize-ai/phoenix/issues/13290)) ### Features Phoenix now lets you compose evaluation strategies in code. Most eval tooling hands you a fixed menu of judge templates. Real evaluation is rarely that tidy. High5/21/2026
arize-phoenix-v15.10.0## [15.10.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v15.9.0...arize-phoenix-v15.10.0) (2026-05-15) ### Features * add trace feedback toolbar to session turns ([#13189](https://github.com/Arize-ai/phoenix/issues/13189)) ([1bd96b9](https://github.com/Arize-ai/phoenix/commit/1bd96b9a824dd2457c6f60e54897a6e1d5d92132)) * **agents:** curate agent model menu ([#13190](https://github.com/Arize-ai/phoenix/issues/13190)) ([de8c915](https://github.com/Arize-ai/phoenix/commit/de8c91579High5/15/2026
arize-phoenix-v15.6.0## [15.6.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v15.5.1...arize-phoenix-v15.6.0) (2026-05-10) ### Features * **agents:** add /agents/{agent_id}/sessions/{session_id}/summary endpoint ([#13095](https://github.com/Arize-ai/phoenix/issues/13095)) ([419c3a0](https://github.com/Arize-ai/phoenix/commit/419c3a06978abce8f611569228438929f8e7b995)) * **agents:** Playground manipulation tools w/ confirmation ([#13093](https://github.com/Arize-ai/phoenix/issues/13093)) ([37dc417](htHigh5/10/2026
arize-phoenix-v15.4.0## [15.4.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v15.3.0...arize-phoenix-v15.4.0) (2026-05-05) ### Features * **agents:** agent set_time_range tool with hardened context injection ([#13022](https://github.com/Arize-ai/phoenix/issues/13022)) ([115c08b](https://github.com/Arize-ai/phoenix/commit/115c08ba093d22ebe91dbc10d3c325fb03e39a79)) * **agents:** ToolPart styles and subcomponents ([#12894](https://github.com/Arize-ai/phoenix/issues/12894)) ([0d4e16b](https://github.comHigh5/5/2026
arize-phoenix-v15.1.0## [15.1.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v15.0.0...arize-phoenix-v15.1.0) (2026-04-30) ### Features * **api:** query annotations by identifier on GET endpoints ([#12952](https://github.com/Arize-ai/phoenix/issues/12952)) ([e2a1de9](https://github.com/Arize-ai/phoenix/commit/e2a1de9274b1434db89bb3aef1957abac3071d20)) * **cli:** add named auth profile management ([#12529](https://github.com/Arize-ai/phoenix/issues/12529)) ([ab62d3d](https://github.com/Arize-ai/phoenHigh4/30/2026
arize-phoenix-v14.15.0## [14.15.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.14.0...arize-phoenix-v14.15.0) (2026-04-26) ### Features * **app:** add sessions_ux flag with Turns/Traces toggle ([#12826](https://github.com/Arize-ai/phoenix/issues/12826)) ([e9cadd5](https://github.com/Arize-ai/phoenix/commit/e9cadd5ded309fbecbec5f9c3cb6ae35fbf2de6a)) * **skills:** add phoenix-skills-audit skill and weekly GHA ([#12863](https://github.com/Arize-ai/phoenix/issues/12863)) ([3d6cc81](https://github.comHigh4/26/2026
arize-phoenix-v14.11.0## [14.11.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.10.0...arize-phoenix-v14.11.0) (2026-04-22) ### Features * **agent:** session summary eval + sidebar-title prompt rewrite ([#12780](https://github.com/Arize-ai/phoenix/issues/12780)) ([fab5d89](https://github.com/Arize-ai/phoenix/commit/fab5d89b130cd14f301ee3b6ed02bbd295f21e0e)) * **app:** show root span name in session turn list ([#12795](https://github.com/Arize-ai/phoenix/issues/12795)) ([c31fd97](https://github.comHigh4/22/2026
arize-phoenix-v14.10.0## [14.10.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.9.1...arize-phoenix-v14.10.0) (2026-04-21) ### Features * **agent:** Display token count for chat sessions ([#12765](https://github.com/Arize-ai/phoenix/issues/12765)) ([c305919](https://github.com/Arize-ai/phoenix/commit/c305919514602acec4319650b9a4e5ea07b0ab07)) ### Bug Fixes * **deps:** pin authlib<1.7.0 ([#12783](https://github.com/Arize-ai/phoenix/issues/12783)) ([cc606d8](https://github.com/Arize-ai/phoenixHigh4/21/2026
arize-phoenix-v14.9.1## [14.9.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.9.0...arize-phoenix-v14.9.1) (2026-04-21) ### Bug Fixes * **db:** wrap Azure AsyncEngine with ObjectProxy instead of patching dispose ([#12777](https://github.com/Arize-ai/phoenix/issues/12777)) ([d37bdfa](https://github.com/Arize-ai/phoenix/commit/d37bdfaa2ad1a4a3d140a5153c3f7320c9dfebb2))High4/21/2026
arize-phoenix-v14.9.0## [14.9.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.8.0...arize-phoenix-v14.9.0) (2026-04-20) ### Features * Add PXI consent and trace-sharing controls ([#12740](https://github.com/Arize-ai/phoenix/issues/12740)) ([ebc9997](https://github.com/Arize-ai/phoenix/commit/ebc9997d0edacfbe53756f340ccf69bbab1a7bbe)) * **agent:** empty-state screen for PXI chat ([#12726](https://github.com/Arize-ai/phoenix/issues/12726)) ([0a5a180](https://github.com/Arize-ai/phoenix/commit/0a5a1High4/20/2026
arize-phoenix-v14.8.0## [14.8.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.7.0...arize-phoenix-v14.8.0) (2026-04-16) ### Features * **db:** add Azure managed identity authentication for PostgreSQL ([#12687](https://github.com/Arize-ai/phoenix/issues/12687)) ([6c53e48](https://github.com/Arize-ai/phoenix/commit/6c53e48b8fd52ddfd99e7f914051eebeb63c39a9))High4/16/2026
arize-phoenix-v14.7.0## [14.7.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.6.0...arize-phoenix-v14.7.0) (2026-04-16) ### Features * session pagination ([#12695](https://github.com/Arize-ai/phoenix/issues/12695)) ([465ff59](https://github.com/Arize-ai/phoenix/commit/465ff595105ae4344d3854762770874d22060cd7)) * trace annotation dataloader ([#12699](https://github.com/Arize-ai/phoenix/issues/12699)) ([8e2effd](https://github.com/Arize-ai/phoenix/commit/8e2effd4312ce6e08e8a2851fcbdb9e654a6303c)) *High4/16/2026
arize-phoenix-v14.6.0## [14.6.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.5.0...arize-phoenix-v14.6.0) (2026-04-15) ### Features * **agent:** fix docs URL formatting in PXI system prompt + add eval harness ([#12677](https://github.com/Arize-ai/phoenix/issues/12677)) ([5dd794b](https://github.com/Arize-ai/phoenix/commit/5dd794bbd6d4153b8a1ea0c6ead881e93fff95f0)) * **app:** list-detail layout for session turns ([#12674](https://github.com/Arize-ai/phoenix/issues/12674)) ([f5951fb](https://githuHigh4/15/2026
arize-phoenix-v14.5.0## [14.5.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.4.0...arize-phoenix-v14.5.0) (2026-04-14) ### Features * Add chat metadata to assistant messages ([#12665](https://github.com/Arize-ai/phoenix/issues/12665)) ([a6f0f7f](https://github.com/Arize-ai/phoenix/commit/a6f0f7f7216ca675d9307f2afcfcee07dc537f28)) * Add span and trace annotation commands to the Phoenix CLI ([#12664](https://github.com/Arize-ai/phoenix/issues/12664)) ([c04a0c3](https://github.com/Arize-ai/phoenix/High4/14/2026
arize-phoenix-v14.4.0## [14.4.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.3.1...arize-phoenix-v14.4.0) (2026-04-14) ### Features * **agent:** Capability menu + Refactor PXI frontend tool wiring around a capability registry ([#12590](https://github.com/Arize-ai/phoenix/issues/12590)) ([0518f16](https://github.com/Arize-ai/phoenix/commit/0518f1632dacd6df7e74e914a3bfdd4047a2f8a1)) ### Bug Fixes * remove pin on graphql-core ([#12657](https://github.com/Arize-ai/phoenix/issues/12657)) ([21b4c27Medium4/14/2026
arize-phoenix-v14.3.1## [14.3.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.3.0...arize-phoenix-v14.3.1) (2026-04-14) ### Bug Fixes * Harden authFetch and add it to dataset upload path ([#12616](https://github.com/Arize-ai/phoenix/issues/12616)) ([62590d2](https://github.com/Arize-ai/phoenix/commit/62590d25d1d8da90a0db2ed19d1291a8a3462220))High4/14/2026
arize-phoenix-v14.3.0## [14.3.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.2.1...arize-phoenix-v14.3.0) (2026-04-14) ### Features * **agent:** assistant agent settings page ([#12637](https://github.com/Arize-ai/phoenix/issues/12637)) ([bca2318](https://github.com/Arize-ai/phoenix/commit/bca23186770e6bf26489704e3bfe33bed42ce838)) * Re-export openinference-core from phoenix-otel with docs ([#12541](https://github.com/Arize-ai/phoenix/issues/12541)) ([1449f3d](https://github.com/Arize-ai/phoenix/Medium4/14/2026
arize-phoenix-v14.2.1## [14.2.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.2.0...arize-phoenix-v14.2.1) (2026-04-10) ### Bug Fixes * remove WebSocket support for GraphQL subscriptions, use HTTP multipart ([#12610](https://github.com/Arize-ai/phoenix/issues/12610)) ([ed77fea](https://github.com/Arize-ai/phoenix/commit/ed77feafa4877ed01f89555002e4be372d3aa4ac))High4/10/2026
arize-phoenix-v14.2.0## [14.2.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.1.1...arize-phoenix-v14.2.0) (2026-04-10) ### Features * add /redirects/projects/:project_name for name-based project URLs ([#12593](https://github.com/Arize-ai/phoenix/issues/12593)) ([afd9584](https://github.com/Arize-ai/phoenix/commit/afd95840791251c2489ce2d83be6c50563148dfd)) ### Documentation * Add Phoenix release notes for 04-02-2026 through 04-07-2026 ([#12588](https://github.com/Arize-ai/phoenix/issues/12588)Medium4/10/2026
arize-phoenix-v14.1.1## [14.1.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.1.0...arize-phoenix-v14.1.1) (2026-04-08) ### Bug Fixes * use dataloader for session annotations to prevent connection exhaustion ([#12585](https://github.com/Arize-ai/phoenix/issues/12585)) ([8549fde](https://github.com/Arize-ai/phoenix/commit/8549fde5ba66a2e98d9f4d8bd5e7cc205212014d))High4/8/2026
arize-phoenix-v14.1.0## [14.1.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v14.0.0...arize-phoenix-v14.1.0) (2026-04-08) ### Bug Fixes * add valid OpenAPI examples for span creation endpoint ([#12371](https://github.com/Arize-ai/phoenix/issues/12371)) ([d74be37](https://github.com/Arize-ai/phoenix/commit/d74be37cefff79313e216ce1ef80993e3c645345)) * **agent:** surface backend tool loop exhaustion ([#12569](https://github.com/Arize-ai/phoenix/issues/12569)) ([c887c93](https://github.com/Arize-ai/phoeMedium4/8/2026
arize-phoenix-client-v2.3.1## [2.3.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v2.3.0...arize-phoenix-client-v2.3.1) (2026-04-07) ### Features * **evals:** deprecate evals 1.0 and remove legacy experiments module ([#12239](https://github.com/Arize-ai/phoenix/issues/12239)) ([15e6415](https://github.com/Arize-ai/phoenix/commit/15e6415105ce4757de905172cbd0e07215d38990)) ### Miscellaneous Chores * release 2.3.1 ([#12572](https://github.com/Arize-ai/phoenix/issues/12572)) ([a33630d](https://githubMedium4/7/2026
arize-phoenix-evals-v3.0.0## [3.0.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-evals-v2.13.0...arize-phoenix-evals-v3.0.0) (2026-04-07) ### ⚠ BREAKING CHANGES * **evals:** deprecate evals 1.0 and remove legacy experiments module ([#12239](https://github.com/Arize-ai/phoenix/issues/12239)) ### Features * **evals:** deprecate evals 1.0 and remove legacy experiments module ([#12239](https://github.com/Arize-ai/phoenix/issues/12239)) ([15e6415](https://github.com/Arize-ai/phoenix/commit/15e6415105ce4757dMedium4/7/2026
arize-phoenix-v14.0.0See [MIGRATION.md](https://github.com/Arize-ai/phoenix/blob/main/MIGRATION.md) ## [14.0.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.23.0...arize-phoenix-v14.0.0) (2026-04-07) ### ⚠ BREAKING CHANGES * **server:** remove /v1/evaluations endpoint and Evaluations plumbing ([#12538](https://github.com/Arize-ai/phoenix/issues/12538)) * **evals:** deprecate evals 1.0 and remove legacy experiments module ([#12239](https://github.com/Arize-ai/phoenix/issues/12239)) * **cMedium4/7/2026
arize-phoenix-client-v2.3.0## [2.3.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v2.2.0...arize-phoenix-client-v2.3.0) (2026-04-03) ### Features * atif to trace trajectory conversion utility ([#12414](https://github.com/Arize-ai/phoenix/issues/12414)) ([28ecfe0](https://github.com/Arize-ai/phoenix/commit/28ecfe023f3d94f97afa36b7161f80e1d316cc39))Medium4/3/2026
arize-phoenix-v13.23.0## [13.23.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.22.2...arize-phoenix-v13.23.0) (2026-04-02) ### Features * bundle TypeScript SDK docs into npm packages ([#12487](https://github.com/Arize-ai/phoenix/issues/12487)) ([1028be5](https://github.com/Arize-ai/phoenix/commit/1028be5ea7400886a2abf64b2c227f66edb791e0)) ### Bug Fixes * **app:** fix broken Playground button in prompts table ([#12511](https://github.com/Arize-ai/phoenix/issues/12511)) ([4a4ddb3](https://githubMedium4/2/2026
arize-phoenix-v13.22.2## [13.22.2](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.22.1...arize-phoenix-v13.22.2) (2026-04-01) ### Bug Fixes * use DISTINCT instead of GROUP BY in ProjectHasTracesDataLoader ([#12495](https://github.com/Arize-ai/phoenix/issues/12495)) ([77bf1a3](https://github.com/Arize-ai/phoenix/commit/77bf1a3e0e287b561e430b74f74bc0fa082ed7f9))Medium4/1/2026
arize-phoenix-v13.22.1## [13.22.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.22.0...arize-phoenix-v13.22.1) (2026-04-01) ### Bug Fixes * replace expensive count queries with hasTraces existence check ([#12490](https://github.com/Arize-ai/phoenix/issues/12490)) ([2d064fc](https://github.com/Arize-ai/phoenix/commit/2d064fc263a70cc5705a535d0070632200d6d922)) * skip redundant header stats refetch on initial mount ([#12491](https://github.com/Arize-ai/phoenix/issues/12491)) ([a10d8ed](https://githubMedium4/1/2026
arize-phoenix-client-v2.2.0## [2.2.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v2.1.0...arize-phoenix-client-v2.2.0) (2026-04-01) ### Features * add GET /v1/user endpoint and phoenix-rest-api skill ([#12274](https://github.com/Arize-ai/phoenix/issues/12274)) ([b5188ea](https://github.com/Arize-ai/phoenix/commit/b5188ea92eeb76ed0155e999b8fa0fc00519f32c)) * add Python 3.14 support (except Windows) ([#12475](https://github.com/Arize-ai/phoenix/issues/12475)) ([50c08e3](https://github.com/Arize-ai/pMedium4/1/2026
arize-phoenix-evals-v2.13.0## [2.13.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-evals-v2.12.0...arize-phoenix-evals-v2.13.0) (2026-04-01) ### Features * add Python 3.14 support (except Windows) ([#12475](https://github.com/Arize-ai/phoenix/issues/12475)) ([50c08e3](https://github.com/Arize-ai/phoenix/commit/50c08e3ff4e41c0693e92b7d3de7dbc41384fad1))Medium4/1/2026
arize-phoenix-v13.22.0## [13.22.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.21.0...arize-phoenix-v13.22.0) (2026-04-01) ### Features * **ui:** updated provider and integration icons, logo icon agent skill ([#12470](https://github.com/Arize-ai/phoenix/issues/12470)) ([8668c43](https://github.com/Arize-ai/phoenix/commit/8668c437d44969b6b52f67d3d4c9f0afce270ba7)) ### Bug Fixes * fail loudly on Windows + Python 3.14 install ([#12480](https://github.com/Arize-ai/phoenix/issues/12480)) ([50d66a3]Medium4/1/2026
arize-phoenix-v13.21.0## [13.21.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.20.0...arize-phoenix-v13.21.0) (2026-04-01) ### Features * add Python 3.14 support (except Windows) ([#12475](https://github.com/Arize-ai/phoenix/issues/12475)) ([50c08e3](https://github.com/Arize-ai/phoenix/commit/50c08e3ff4e41c0693e92b7d3de7dbc41384fad1)) * **agent:** Improve session summaries ([#12471](https://github.com/Arize-ai/phoenix/issues/12471)) ([f1750a9](https://github.com/Arize-ai/phoenix/commit/f1750a920aMedium4/1/2026
arize-phoenix-v13.20.0## [13.20.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.19.2...arize-phoenix-v13.20.0) (2026-03-29) ### Features * **rest-api:** DELETE /prompt_versions/{id}/tags/{tag_name} ([#12427](https://github.com/Arize-ai/phoenix/issues/12427)) ([0c61d16](https://github.com/Arize-ai/phoenix/commit/0c61d1629c683a8736df893e296fc9d7c9d5a45f)) * **rest-api:** DELETE /prompts/{prompt_identifier} ([#12426](https://github.com/Arize-ai/phoenix/issues/12426)) ([ac9ffbe](https://github.com/AriMedium3/30/2026
arize-phoenix-v13.19.2## [13.19.2](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.19.1...arize-phoenix-v13.19.2) (2026-03-28) ### Bug Fixes * **ui:** fix model menu search losing focus on first keystroke ([#12417](https://github.com/Arize-ai/phoenix/issues/12417)) ([f5b2cc2](https://github.com/Arize-ai/phoenix/commit/f5b2cc2eb49a2d64cea1208bcba397adccc117c8))Medium3/28/2026
arize-phoenix-v13.19.1## [13.19.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.19.0...arize-phoenix-v13.19.1) (2026-03-27) ### Bug Fixes * **TracesTable:** update interface for additional spans row and adjust GraphQL fragments ([#12385](https://github.com/Arize-ai/phoenix/issues/12385)) ([0f38e06](https://github.com/Arize-ai/phoenix/commit/0f38e06638c5e18fcb349514649b44574474343f)) ### Documentation * **cli:** update phoenix CLI skill and docs for noun-verb commands ([#12393](https://github.coMedium3/27/2026
arize-phoenix-v13.19.0## [13.19.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.18.2...arize-phoenix-v13.19.0) (2026-03-26) ### Features * add PromptInput compound component for AI interactions ([#12353](https://github.com/Arize-ai/phoenix/issues/12353)) ([729a56f](https://github.com/Arize-ai/phoenix/commit/729a56fc832ffc6b7ee3a011f9f5a2bbd32e6aee)) * **agent-chat:** collapse tool calls into expandable pool + streaming perf ([#12360](https://github.com/Arize-ai/phoenix/issues/12360)) ([39acfcf](htMedium3/26/2026
arize-phoenix-v13.18.2## [13.18.2](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.18.1...arize-phoenix-v13.18.2) (2026-03-24) ### Bug Fixes * **deps:** update arize-phoenix-evals to 2.12.0 ([#12346](https://github.com/Arize-ai/phoenix/issues/12346)) ([c42aed2](https://github.com/Arize-ai/phoenix/commit/c42aed261e0c6473a0357c8120d4e45272828843))Medium3/24/2026
arize-phoenix-evals-v2.12.0## [2.12.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-evals-v2.11.0...arize-phoenix-evals-v2.12.0) (2026-03-24) ### Features * **evals:** accept structured data eval inputs ([#12095](https://github.com/Arize-ai/phoenix/issues/12095)) ([5f33727](https://github.com/Arize-ai/phoenix/commit/5f3372794fc2dfe0184d08f7d5d44f39284dbe67)) ### Bug Fixes * **evals:** allow prompt_template and kwargs in built-in classification evaluators ([#11984](https://github.com/Arize-ai/phoenix/issMedium3/24/2026
arize-phoenix-v13.18.1## [13.18.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.18.0...arize-phoenix-v13.18.1) (2026-03-24) ### Bug Fixes * Pin LiteLLM <1.82.7 to mitigate supply chain attack ([#12342](https://github.com/Arize-ai/phoenix/issues/12342)) ([48970b6](https://github.com/Arize-ai/phoenix/commit/48970b62815a8230b38f67f4246c69cab3d473c0))Medium3/24/2026
arize-phoenix-v13.18.0## [13.18.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.17.0...arize-phoenix-v13.18.0) (2026-03-24) ### Features * **app:** add prompt version diff view ([#12326](https://github.com/Arize-ai/phoenix/issues/12326)) ([0e9e76b](https://github.com/Arize-ai/phoenix/commit/0e9e76bba81d2b163d5e89b6e82529842fdc6c1a)) * Replace all markdown rendering with streamdown ([#12320](https://github.com/Arize-ai/phoenix/issues/12320)) ([d6a64d5](https://github.com/Arize-ai/phoenix/commit/d6aMedium3/24/2026
arize-phoenix-v13.17.0## [13.17.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.16.0...arize-phoenix-v13.17.0) (2026-03-23) ### Features * **agent:** implement experimental px-gql simulated bash tool ([#12251](https://github.com/Arize-ai/phoenix/issues/12251)) ([843fa8f](https://github.com/Arize-ai/phoenix/commit/843fa8f54583b5b4be0b4cf47f15bb85a391e996)) * copy spanID to clipboard ([#12321](https://github.com/Arize-ai/phoenix/issues/12321)) ([a7ded9a](https://github.com/Arize-ai/phoenix/commit/a7Medium3/23/2026
arize-phoenix-v13.16.0## [13.16.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.15.0...arize-phoenix-v13.16.0) (2026-03-22) ### Features * Add backend skill ([#12117](https://github.com/Arize-ai/phoenix/issues/12117)) ([cc8de3b](https://github.com/Arize-ai/phoenix/commit/cc8de3b9d23a2579f50f9c76e20efeb7adf432c7)) * add configurable package manager preference per language ([#12140](https://github.com/Arize-ai/phoenix/issues/12140)) ([bf35656](https://github.com/Arize-ai/phoenix/commit/bf35656c7b548Low3/22/2026
arize-phoenix-client-v2.1.0## [2.1.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v2.0.1...arize-phoenix-client-v2.1.0) (2026-03-18) ### Features * **client:** add span filter params to getSpans ([#12203](https://github.com/Arize-ai/phoenix/issues/12203)) ([91949d7](https://github.com/Arize-ai/phoenix/commit/91949d7aa63acff7110ec79518d9ad9ce711e277))Low3/18/2026
arize-phoenix-client-v2.0.1## [2.0.1](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v2.0.0...arize-phoenix-client-v2.0.1) (2026-03-14) ### Bug Fixes * **client:** add server version gating with capability requirements ([#12122](https://github.com/Arize-ai/phoenix/issues/12122)) ([9769f90](https://github.com/Arize-ai/phoenix/commit/9769f906ae0caef8e19f88e25e0ea545ee399d72))Low3/14/2026
arize-phoenix-v13.15.0## [13.15.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.14.0...arize-phoenix-v13.15.0) (2026-03-13) ### Features * Add `phoenix db migrate` subcommand for standalone migrations ([#12071](https://github.com/Arize-ai/phoenix/issues/12071)) ([11360a6](https://github.com/Arize-ai/phoenix/commit/11360a6f9e200e6bdff0cb4e5ee952aa174107ee)) * **server:** add GET /v1/projects/{project_identifier}/traces endpoint ([#12057](https://github.com/Arize-ai/phoenix/issues/12057)) ([beee817]Low3/13/2026
arize-phoenix-client-v2.0.0## [2.0.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v1.31.0...arize-phoenix-client-v2.0.0) (2026-03-11) ### ⚠ BREAKING CHANGES * **client:** `client.annotations` has been removed. Use `client.spans` instead. ### Features * add Cerebras, Fireworks, Groq, and Moonshot as first-class providers ([#11938](https://github.com/Arize-ai/phoenix/issues/11938)) ([df94203](https://github.com/Arize-ai/phoenix/commit/df94203fa621bae9928d96249382380aa4be5443)) * add Perplexity and Low3/11/2026
arize-phoenix-v13.14.0## [13.14.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.13.0...arize-phoenix-v13.14.0) (2026-03-11) ### Features * add phoenix-pr-screenshot slash command skill ([#12051](https://github.com/Arize-ai/phoenix/issues/12051)) ([4c4c6c7](https://github.com/Arize-ai/phoenix/commit/4c4c6c70054c96e659ec7eecf69768dea73d6623)) * **client:** add session conversation API to Python and TypeScript clients ([#11974](https://github.com/Arize-ai/phoenix/issues/11974)) ([83b7f68](https://gitLow3/11/2026
arize-phoenix-v13.13.0## [13.13.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.12.0...arize-phoenix-v13.13.0) (2026-03-10) ### Features * add PHOENIX_ALLOWED_PROVIDERS env var to filter model providers in UI ([#12056](https://github.com/Arize-ai/phoenix/issues/12056)) ([ba97d59](https://github.com/Arize-ai/phoenix/commit/ba97d59204a8f523eeb28558feea8a855ee91b7c)) * add PHOENIX_HIDDEN_PROVIDERS env var to hide model providers from UI ([#11986](https://github.com/Arize-ai/phoenix/issues/11986)) ([0Low3/10/2026
arize-phoenix-v13.12.0## [13.12.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.11.0...arize-phoenix-v13.12.0) (2026-03-09) ### Features * Add feature-flagged tracing onboarding empty state ([#11853](https://github.com/Arize-ai/phoenix/issues/11853)) ([6e17c3b](https://github.com/Arize-ai/phoenix/commit/6e17c3be18f541a7f1ed92a20782b98578f7aa20)) * add PackageManagerCommandBlock component ([#11968](https://github.com/Arize-ai/phoenix/issues/11968)) ([9e980de](https://github.com/Arize-ai/phoenix/comLow3/9/2026
arize-phoenix-v13.11.0## Highlights ### 🎉 Perplexity AI & Together AI Now in Playground Phoenix now supports **Perplexity AI** and **Together AI** as built-in providers in the playground. Both use OpenAI-compatible APIs — just set your API key and start chatting. ![Perplexity and Together AI support](https://storage.googleapis.com/arize-phoenix-assets/assets/images/together_perplexity_support.png) | Provider | API Key Env Var | Base URL | |----------|----------------|----------| | Perplexity AI | `PERPLEXITY_APILow3/8/2026
arize-phoenix-v13.10.0## Highlights ### 🎉 New First-Class Providers in Playground Phoenix now supports **Cerebras**, **Fireworks AI**, **Groq**, and **Moonshot (Kimi)** as first-class providers in the playground. All four use OpenAI-compatible APIs — no new dependencies required. Just set the appropriate API key environment variable and start chatting. ![AI Providers in Phoenix](https://storage.googleapis.com/arize-phoenix-assets/assets/images/ai_providers.png) | Provider | API Key Env Var | |----------|--------Low3/8/2026
arize-phoenix-v13.9.0## [13.9.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.8.0...arize-phoenix-v13.9.0) (2026-03-07) ### Features * add record icon ([#11928](https://github.com/Arize-ai/phoenix/issues/11928)) ([6190c91](https://github.com/Arize-ai/phoenix/commit/6190c91fe1e1cdbea82ec2cc65ba1688aedbeb9e)) * **api:** add trace_id filter to GET spans REST endpoints ([#11895](https://github.com/Arize-ai/phoenix/issues/11895)) ([99cd8ba](https://github.com/Arize-ai/phoenix/commit/99cd8ba68fdeaf93f9Low3/7/2026
arize-phoenix-client-v1.31.0## [1.31.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-client-v1.30.0...arize-phoenix-client-v1.31.0) (2026-03-06) ### Features * **client:** add session retrieval methods to Python client SDK ([#11879](https://github.com/Arize-ai/phoenix/issues/11879)) ([3669813](https://github.com/Arize-ai/phoenix/commit/3669813c7486b128d8858de6ef1cffa3e8d5c020)) * **client:** add timeout and list_sessions alias to sessions API ([#11897](https://github.com/Arize-ai/phoenix/issues/11897)) ([a4Low3/6/2026
arize-phoenix-v13.8.0## [13.8.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.7.0...arize-phoenix-v13.8.0) (2026-03-04) ### Features * add integration icons for claude, langgraph ([#11823](https://github.com/Arize-ai/phoenix/issues/11823)) ([ccedc3d](https://github.com/Arize-ai/phoenix/commit/ccedc3d587349a3563df1e3ac73ce6d1907d29c1)) * **agents:** pydantic vercel data stream protocol ([#11689](https://github.com/Arize-ai/phoenix/issues/11689)) ([bb65bf7](https://github.com/Arize-ai/phoenix/commiLow3/4/2026
arize-phoenix-v13.7.0## [13.7.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.6.0...arize-phoenix-v13.7.0) (2026-03-02) ### Features * update container image to debian13 ([#11835](https://github.com/Arize-ai/phoenix/issues/11835)) ([188e5f1](https://github.com/Arize-ai/phoenix/commit/188e5f19dc5b03d1bc899d02f3076f8bb4020950)) ### Bug Fixes * **deps:** update arize-phoenix-client to 1.30.0 ([#11824](https://github.com/Arize-ai/phoenix/issues/11824)) ([4d97cdb](https://github.com/Arize-ai/phoeniLow3/2/2026
arize-phoenix-otel-v0.15.0## [0.15.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-otel-v0.14.0...arize-phoenix-otel-v0.15.0) (2026-03-02) ### Features * **otel:** support python 3.10 - 3.14 for arize-phoenix-otel ([#11831](https://github.com/Arize-ai/phoenix/issues/11831)) ([bca6282](https://github.com/Arize-ai/phoenix/commit/bca62828e00951948b12a4bd96a47938bd11b267)) ### Bug Fixes * update slack invitation link ([#11612](https://github.com/Arize-ai/phoenix/issues/11612)) ([316833e](https://github.comLow3/2/2026
arize-phoenix-v13.6.0## [13.6.0](https://github.com/Arize-ai/phoenix/compare/arize-phoenix-v13.5.0...arize-phoenix-v13.6.0) (2026-03-02) ### Features * **app:** add inline document annotation UI for retriever spans ([#11688](https://github.com/Arize-ai/phoenix/issues/11688)) ([54fc287](https://github.com/Arize-ai/phoenix/commit/54fc2870ca8c24a276de1afa51ae8b86cccc370e)) * **cli:** add sessions and session commands for multi-turn conversation support ([#11795](https://github.com/Arize-ai/phoenix/issues/11795)) ([bLow3/2/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

trulensEvaluation and Tracking for LLM Experiments and AI Agentstrulens-2.8.1
.claudeThe Ultimate Claude Code Toolkit — 127 skills, 86 agents, 109 marketplace repos (11,700+ community skills), 30 commands, 8 hooks, GSD framework. Drop-in ~/.claude config that auto-activates the right master@2026-06-03
octobenchBenchmark and compare LLM tool, configuration, and prompt setups using a shared case framework with automated scoring and telemetry.main@2026-06-02
mlflowThe open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controllinv3.13.0
ruby_llm-contractHandle LLM output variance for ruby_llm — retry on malformed JSON or rule violations, escalate to a smarter model, measure variance on datasets, gate CI on regressions.v0.9.0

More from Arize-ai

openinferenceOpenTelemetry Instrumentation for AI Observability

More in Testing

vector-db-benchmarkFramework for benchmarking vector search engines
GitoAn AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.
mxcliMendix cli tool, a headless way to work with Mendix projects. Enables Mendix projects for use with 3rd party agentic coding tools like Claude Code and Copilot. Includes a starlark linter for quality v
llm_context_benchmarks 📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI), automatic hardware detection (optimiz