AI tool intelligence

Find the right AI products for the work.

Our live catalog contains 2,444 researched AI products. Each record keeps current product positioning, fit, limitations, pricing signals, and official destinations together for a clearer decision.

Search products, capabilities, and workflowsBrowse the index ↓
2,444AI products in the catalog
DatedAvailability and evidence checks
IndependentFit, limitations, and alternatives

Public AI tool catalog

Search this public selection by the work you need to improve.

Search the complete catalog by product, capability, workflow, category, or tag. Every result opens a profile built from the same live record.

EA
Catalog evaluation

Developer tools

Evidently AI

Evidently AI is an open-source framework for evaluating, testing, and monitoring LLM applications, RAG systems, AI agents, and predictive machine-learning models. Teams can use built-in or custom metrics, generate test cases, run evaluations locally or in the cloud, and track quality over time.

LLM evaluationML monitoringData driftRAG evaluationOpen source
Review
MA
Catalog evaluation

AI agents

Magick

Magick is an open-source visual IDE for creating, testing, deploying, and managing AI agents. Its node-based AIDE lets users connect logic, data, events, language models, and integrations into agent workflows that can be deployed through the Magick Engine.

Visual programmingNode-based workflowsLLMsDiscordSlack
Review
AG
Discontinued record

AI agent builders

AgentRunner

AgentRunner is a beta platform for creating, testing, versioning, and deploying automation agents through a visual node editor. Teams can connect AI providers and other applications through APIs, organize agents into projects, and use run logs to inspect workflow behavior.

Visual workflowsLLM integrationAPI deploymentVersion controlRun logs
Review
QV
Discontinued record

Prompt engineering

Query Vary

Query Vary's official documentation describes tools for designing, testing, and refining LLM prompts. Its main website could not be reached and its signup app returned an error during verification, so current product availability and commercial terms could not be confirmed.

LLM TestingPrompt EngineeringModel Comparison
Review

How the index works

A catalog built for decisions, not rankings.

Commercial relationships can fund the research. They never change product status, fit, limitations, evidence, or the alternatives we show.

Verify what exists

We check availability, product direction, pricing signals, and when the supporting evidence was last reviewed.

Evaluate operational fit

We assess the work it supports, integration requirements, ownership, risk, and where human judgment remains necessary.

Keep the comparison honest

Commercial relationships are disclosed, while credible limitations and alternatives stay visible.

Evaluating a product for a live workflow?

Bring the decision to our engineers