The independent directory for AI agents that ship real work.
Hands-on reviews, side-by-side comparisons, and curated picks across coding agents, agent frameworks, and Model Context Protocol servers.
Tracking 210+ agents, 35+ frameworks, and 30+ MCP servers.
Start with the work you need to ship
Editor’s picks
Tools we recommend right now, tested and tracked.
Claude Code
Anthropic's official terminal-native AI coding agent
Cursor
AI-first code editor built on top of VS Code
Retell AI
Low-latency voice agent platform with emotion-adaptive dialogue for sales and support
Vapi
Developer-focused voice AI platform for building production-grade voice agents via API
Devin
Autonomous AI software engineer that works on tickets end to end
ElevenLabs
AI voice cloning and text-to-speech platform for audiobooks, dubbing, and voice agents
Browse by category
Find the kind of agent that matches the kind of work you do.
Coding agents
Pair programmers and autonomous code editors
Research agents
Deep research, reading, and synthesis
Browser agents
Web automation and computer use
Writing agents
Long-form drafting and editing
Support agents
Ticket deflection and live customer chat
Workflow agents
Multi-step automation across tools
MCP servers worth knowing
Connect agents to the tools, data, and workflows they need to act.
AWS MCP Server
Query S3, Lambda, DynamoDB, CloudWatch, and more AWS services from any MCP-compatible AI agent
Brave Search
Real-time web search for AI agents with a privacy-first independent index
Cloudflare MCP Server
Manage Workers, Pages, R2, KV, D1, DNS, and Zero Trust from any MCP-compatible AI agent
Exa MCP Server
Give AI agents semantic web search built for machine consumption, not human browsing
Frameworks for builders
Open-source toolkits to build and ship your own agents.
Agency Swarm
Multi-agent framework built on OpenAI Assistants API with role-based agents and structured communication
AgentScope
Visual-first multi-agent framework built for distributed Python workflows
Agno
High-performance Python framework for multi-modal agents and teams
Arize Phoenix
Open-source LLM observability and evaluation with native OpenTelemetry tracing and self-hosting
From the blog
Deep dives, guides, and field notes on agentic tooling.
Building something agents should know about?
Submit your agent, framework, or MCP server. Independent review, no pay-to-play.