Which AI tool for which job.

AI pair programming in your terminal.

• Pair programming in the terminal
• Git-friendly edits

Coding agent and development environment, usable from a CLI and runner on your own machine or in hosted orbs.

• Coding agent + dev environment
• CLI runner on your machine

Anthropic's agentic coding tool: it understands your codebase, edits files and runs commands.

• Agentic coding in the terminal
• Large codebase edits

Open-source coding agent with Plan/Act modes, MCP integration and terminal-first workflows; available as SDK, IDE extension or CLI.

• Open-source IDE agent
• Bring your own model

AI coding agent and editor: hand off tasks to agents that turn ideas into code.

• AI-first editor
• Hand off tasks to agents

AI coding agent / software engineer with parallel cloud agents for engineering teams. Devin Desktop (devin.ai/desktop) manages local and cloud agents; windsurf.com now redirects there.

• Parallel cloud agents
• Delegating engineering tasks

Open-source AI agent from Google that brings Gemini directly into your terminal.

• Terminal agent with Gemini
• Open-source CLI agent

Works from an open issue to reviewing and merging a pull request, in your editor, terminal, desktop and on GitHub.

• Issue-to-PR workflow
• Inside existing GitHub workflow

OpenAI's lightweight coding agent that runs in your terminal. Source on GitHub.

• Agentic coding in the terminal
• Open-source CLI agent

The open source AI coding agent.

• Open-source coding agent
• Provider-agnostic terminal agent

AI builder for websites, apps and prototypes from plain-language prompts.

• Prompt-to-app prototypes
• Websites and apps

Full-stack AI development platform for building, iterating on and deploying web apps using natural language.

• Prompt-to-web-app
• Full-stack web apps

Describe what you want and Replit builds an app or website.

• Prompt-to-app
• Browser-based building

Vercel's collaborative AI assistant to design, iterate and scale full-stack web applications.

• UI and full-stack web apps
• Vercel ecosystem

Unified TypeScript SDK for building AI apps with streaming, fallbacks and multi-model support, from Vercel.

• TypeScript AI apps
• Streaming UIs and multi-model apps

Multi-agent platform and open-source framework.

• Multi-agent systems

Open agent engineering platform for building, controlling and governing agents.

• Agent engineering platform
• Python / JS agent building

AI agents for document OCR and workflows (LlamaParse).

• Document agents
• Document OCR and workflows

TypeScript framework for agents with memory, tools, MCP and observability.

• TypeScript agents
• Memory, tools, MCP

Lightweight, powerful framework for multi-agent workflows.

• Multi-agent workflows in Python

Python AI framework: agents, realtime voice, image generation and embeddings, typed end to end.

• Typed Python agents

Platform for production-ready agentic workflows: agents, knowledge pipelines, models and tools on one canvas; cloud, VPC or self-hosted.

• Visual agentic workflows
• Self-hostable agent platform

Specification and documentation for the Model Context Protocol (MCP).

• Connect agents to tools and data
• Build MCP servers

Workflow automation platform that combines AI capabilities with business process automation.

• Workflow automation with AI
• Glue between apps

Run machine learning models on serverless GPUs on Cloudflare's network.

• Serverless inference at the edge

AI community advancing and democratizing AI through open source and open science. Star count shown is for its transformers library.

• Find open models
• Open source and open science

Desktop app for local models; its Bionic agent creates documents, slides, PDFs and software with local or frontier open models.

• Local models with a desktop app

Run and build with open AI models locally or in the cloud on macOS, Windows and Linux.

• Run models locally
• Local dev against open models

Unified interface for models; find the best models and prices for your prompts.

• One API for many models
• Compare models and prices

High-throughput, memory-efficient inference and serving engine for LLMs.

• Self-hosted high-throughput serving

Claude Platform documentation and API.

• Build with Claude models

Google's Gemini Developer API and Google AI Studio, plus Gemma open models.

• Build with Gemini and Gemma

Get an API key at console.x.ai and build with Grok; also image, video and voice APIs. The site is currently branded SpaceXSI.

• Build with Grok models

Guides, API docs and examples for the OpenAI API.

• Build with OpenAI models

Open-source agent evals and observability: trace, evaluate and improve agents on one platform.

• Tracing and evals for agents

Gives your agents access to the whole web.

• Browser access for agents

Search API for AI agents that need real-time web data, deep research and structured content.

• Search API for agents

Web data API for AI agents.

• Web data for agents

Postgres development platform: database, authentication, instant APIs, realtime, functions, storage and vector embeddings.

• Backend for vibe-coded apps

Agentic infrastructure: "the autonomous stack for every app and agent" (Vercel's own tagline).

• Deploy AI apps