Open-source AI observability and evaluation toolkit for Jupyter, local scripts, and LLM applications.
Arize Phoenix is an open-source toolkit for AI observability and evaluation. It runs in Jupyter notebooks, local scripts, or any Python environment and provides tracing, evaluation, and prompt engineering workflows without requiring a hosted service.
Phoenix supports OpenTelemetry, LLM tracing, embedding visualization, and RAG evaluation. It is the free entry point to the Arize platform and is widely adopted by AI developers and researchers for local debugging and experimentation.
| Attribute | Arize Phoenix | Agent Arena, Evals | Digital World Models | PromptTools | |
|---|---|---|---|---|---|
| Provider | |  |  |  | |
| Founded | 2020 | 2026 | 2023 | 2023 | |
| Sells To | B2B, Enterprise | B2B, Developer | — | Enterprise | |
| Pricing Model | Recurring, SaaS, Subscription | B2B Subscription | — | Recurring, Software | |
| Ownership | Venture-backed | Private | Venture-backed | Venture-backed |
Provider
Founded 2020
Sells To B2B, Enterprise
Pricing Model Recurring, SaaS, Subscription
Ownership Venture-backed
Founded 2026
Sells To B2B, Developer
Pricing Model B2B Subscription
Ownership Private
Provider
Founded 2023
Sells To —
Pricing Model —
Ownership Venture-backed
Provider
Founded 2023
Sells To Enterprise
Pricing Model Recurring, Software
Ownership Venture-backed
Open-source LLM engineering platform for tracing, prompt management, evaluations, and analytics.
Observability and evaluation platform for shipping quality AI agents at scale.
Observability for LLM applications and AI agents, tracing model calls, tool invocations, and agent handoffs.
Open-source AI SDK with a unified interface across multiple providers, no vendor lock-in.
Pydantic validation, agent runtime, and observability across one lifecycle.
Evidently AI's ML Monitoring is an open-source Python library for ML and LLM model monitoring and evaluation.
Typed Pydantic AI agents with validated outputs and observability.
Interactive observability and management UI for Mastra agents with metrics, traces, and team collaboration.
Monitoring platform that detects silent failures in production AI agents.
Governed, citation-grounded assistant embedding Summarize, Analyze, and Create in public-safety workflows on Peregrine Foundation data.
Open-source LLM engineering platform for tracing, prompt management, evaluations, and analytics.
Observability and evaluation platform for shipping quality AI agents at scale.
Observability for LLM applications and AI agents, tracing model calls, tool invocations, and agent handoffs.
Platform for building, testing, and monitoring AI agents in production.
Open-source AI SDK with a unified interface across multiple providers, no vendor lock-in.
Pydantic validation, agent runtime, and observability across one lifecycle.
Evidently AI's ML Monitoring is an open-source Python library for ML and LLM model monitoring and evaluation.
Typed Pydantic AI agents with validated outputs and observability.
Interactive observability and management UI for Mastra agents with metrics, traces, and team collaboration.
Monitoring platform that detects silent failures in production AI agents.
Opik is Comet's open-source AI observability and LLM evaluation platform for agentic applications.
Governed, citation-grounded assistant embedding Summarize, Analyze, and Create in public-safety workflows on Peregrine Foundation data.
