LIVE
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms

AI Agents

Discover AI agents, frameworks, and tools shaping the ecosystem.

A decade ago, software was what you wrote. Today, software is what an AI writes while you watch. AI agents are the next shift: autonomous systems that perceive their environment, make decisions, take action, and iterate. They're not just chatbots that answer questions. They're systems that complete multi-step tasks independently: writing code, running tests, debugging, browsing the web, filing bugs, drafting reports.

Agents are specialized by domain. Coding agents like GitHub Copilot and Cursor use Claude or GPT-4 with deep IDE integration and version control awareness. They understand context beyond a single file. Research agents like Perplexity use web search, citation tracking, and academic database access to synthesize knowledge. Creative agents handle content generation, design, and copywriting. General-purpose agents like multi-turn Claude conversations can orchestrate workflows across multiple tools. Frameworks like LangChain, CrewAI, and Anthropic's Model Context Protocol (MCP) abstract away the implementation details and let you build agents by composition.

This directory catalogs agents and frameworks we're tracking. We curate this list based on production maturity, community adoption, and technical capability. For a deeper dive into what agents are, their capabilities, and how they'll reshape work, see our explainer on what are AI agents. If you're building an agent, the resources section below has links to documentation for the major frameworks.

Agent Directory

Claude Code

AnthropicCoding Agents

An agentic CLI tool that lets Claude operate directly in your terminal, reading files, editing code, running commands, and managing git workflows autonomously.

Usage-based via Claude API

Launched 2025

Visit

Cursor

AnysphereCoding Agents

An AI-native code editor built on VS Code that provides inline code generation, multi-file editing, and codebase-aware chat powered by multiple foundation models.

Free tier, Pro $20/mo, Business $40/mo

Launched 2023

Visit

GitHub Copilot

GitHub / MicrosoftCoding Agents

An AI pair programmer integrated into popular editors that suggests code completions, generates functions from comments, and offers chat-based coding assistance.

Individual $10/mo, Business $19/mo, Enterprise $39/mo

Launched 2022

Visit

Windsurf

CodeiumCoding Agents

An AI-powered IDE that combines copilot and agent capabilities, allowing flows where the AI and developer collaborate on code changes across an entire project.

Free tier, Pro $15/mo, Teams $30/mo

Launched 2024

Visit

Perplexity

Perplexity AIResearch Agents

An AI-powered answer engine that searches the web in real time, synthesizes information from multiple sources, and provides cited responses to complex questions.

Free tier, Pro $20/mo

Launched 2022

Visit

Elicit

Elicit Inc.Research Agents

A research assistant that helps find and analyze academic papers, extract key claims, and summarize findings across large bodies of scientific literature.

Free tier, Plus $10/mo, Enterprise custom

Launched 2021

Visit

Consensus

Consensus NLPResearch Agents

A search engine that uses AI to find and synthesize results from peer-reviewed scientific research, providing evidence-based answers with citations.

Free tier, Premium $9.99/mo

Launched 2022

Visit

ChatGPT

OpenAIGeneral / Personal Agents

A general-purpose AI assistant that can handle conversation, writing, coding, analysis, and web browsing, with plugin and custom GPT support for specialized tasks.

Free tier, Plus $20/mo, Team $25/mo, Enterprise custom

Launched 2022

Visit

Gemini

GoogleGeneral / Personal Agents

Google's multimodal AI assistant with deep integration into Google Workspace, Search, and Android, capable of handling text, images, code, and long documents.

Free tier, Advanced $19.99/mo (included with Google One AI Premium)

Launched 2023

Visit

Claude

AnthropicGeneral / Personal Agents

A helpful AI assistant known for nuanced instruction-following, long-context understanding, and careful reasoning across writing, analysis, coding, and research tasks.

Free tier, Pro $20/mo, Team $25/mo, Enterprise custom

Launched 2023

Visit

Midjourney

Midjourney Inc.Creative Agents

A leading AI image generation tool that creates high-quality, artistic images from text prompts, known for its distinctive aesthetic style and photorealistic output.

Basic $10/mo, Standard $30/mo, Pro $60/mo

Launched 2022

Visit

DALL-E 3

OpenAICreative Agents

OpenAI's image generation model integrated into ChatGPT and available via API, offering precise prompt adherence and the ability to render text within images.

Included with ChatGPT Plus, API usage-based

Launched 2023

Visit

Suno

Suno Inc.Creative Agents

An AI music generation platform that creates full songs with vocals, instruments, and lyrics from text prompts or custom lyrics input.

Free tier, Pro $10/mo, Premier $30/mo

Launched 2023

Visit

LangChain

LangChain Inc.Frameworks & Platforms

An open-source framework for building LLM-powered applications with chains, agents, retrieval-augmented generation, and memory, supporting multiple model providers.

Open source (LangSmith platform has paid tiers)

Launched 2022

Visit

CrewAI

CrewAI Inc.Frameworks & Platforms

A framework for orchestrating role-playing AI agents that collaborate on complex tasks, allowing developers to define agent roles, goals, and delegation patterns.

Open source, Enterprise cloud plans available

Launched 2024

Visit

AutoGen

MicrosoftFrameworks & Platforms

An open-source framework for building multi-agent conversational systems where multiple AI agents can collaborate, debate, and coordinate to solve tasks.

Open source

Launched 2023

Visit

OpenAI Assistants API

OpenAIFrameworks & Platforms

A platform API for building AI assistants with persistent threads, file retrieval, code interpretation, and function calling built into OpenAI's hosted infrastructure.

Usage-based via OpenAI API

Launched 2023

Visit

Model Context Protocol (MCP)

AnthropicFrameworks & Platforms

An open protocol that standardizes how AI applications connect to external data sources and tools, enabling plug-and-play integrations for any MCP-compatible client.

Open source protocol

Launched 2024

Visit

Build an Agent

Resources and documentation to help you build your own AI agents.