AI Agents
Autonomous AI agents and agent frameworks that plan, use tools, and execute multi-step tasks
Dify LLM App Development Platform
Dify is an open-source LLM application development platform that combines visual workflow orchestration, a built-in RAG engine, and Agent capabilities. It lets developers and non-technical users quickly build, test, and deploy AI-powered apps with support for multiple model providers and seamless API integration.
LangGraph
LangGraph is a low-level orchestration framework from the LangChain team for building stateful, multi-step agent workflows. It provides fine-grained control over execution flow with persistent state, human-in-the-loop checkpoints, and cycle support — ideal for complex agents that need more than simple chain sequencing.
CrewAI
CrewAI is an open-source framework for orchestrating role-playing, autonomous AI agents that collaborate to complete complex tasks. You define agents with specific roles, goals, and tools, then combine them into crews that work together — ideal for building multi-agent systems for research, analysis, and automation.
Gemini CLI
Gemini CLI is an open-source command-line AI agent from Google that brings Gemini models directly into your terminal. It handles coding assistance, file analysis, and automation tasks without leaving the command line, with multi-turn conversation support and easy integration into existing developer workflows.
Claude Code
Claude Code is Anthropic's agentic coding tool that works in your terminal and editor, understanding your entire codebase to plan, write, and refactor code autonomously. It handles multi-file changes, runs tests, and integrates with Git workflows — designed for developers who want an AI collaborator, not just autocomplete.
GitHub Copilot
GitHub Copilot is the most widely adopted AI pair programmer, offering inline code completions, contextual chat, and an autonomous coding agent deeply integrated with GitHub and popular IDEs. It draws on your repository context to suggest relevant code, review changes, and even complete entire tasks from issues.
OpenAI Codex
OpenAI Codex is a cloud-based software engineering agent that runs coding tasks in isolated sandboxes, handling feature development, bug fixes, and pull requests in parallel. Each task runs independently with its own environment, letting teams delegate multiple engineering tasks simultaneously and review the results as PRs.
Cline
Cline is an open-source autonomous coding agent for VS Code that can create and edit files, execute terminal commands, and browse the web — all with human approval at each step. It works with many model providers including Anthropic, OpenAI, and local models, giving developers full control over cost and privacy.
Aider
Aider is a lightweight, terminal-based AI pair programming tool that makes Git-aware edits across multiple files and commits changes automatically with sensible messages. It works with most popular LLMs, maps your entire repository for context, and suits developers who prefer staying in the command line.
Windsurf Editor
Windsurf is an AI-native code editor built around agentic flows that keep you and the AI working from a shared understanding of your codebase. Its Cascade agent handles multi-step tasks with deep context awareness, combining autonomous execution with real-time collaboration in a polished editor experience.
v0 by Vercel
v0 is Vercel's generative UI tool that turns natural-language prompts into production-ready React and Tailwind components. It iterates through multiple design variations, supports shadcn/ui out of the box, and lets you copy code directly into your project — dramatically speeding up frontend prototyping and development.
Bolt.new
Bolt is StackBlitz's AI web builder that turns prompts into full-stack apps running instantly in the browser via WebContainers. Unlike preview-only tools, you get editable source code, package installation, and one-click deployment — ideal for rapid prototyping and shipping small products fast.
Lovable
Lovable is an AI app builder that turns plain-language ideas into working web applications with authentication, databases, and deployment built in. It targets founders and product teams who want to validate ideas quickly, generating real editable code with Supabase integration rather than locked-in templates.
Replit AI
Replit is a cloud IDE with an AI agent that builds, runs, and deploys applications end to end — from prompt to hosted product in one place. Its Agent handles multi-step development tasks including database setup and deployment, making it popular for rapid prototyping without local environment configuration.
AutoGen
AutoGen is Microsoft's open-source framework for building multi-agent AI systems where agents converse with each other, use tools, and collaborate to solve complex tasks. It supports flexible conversation patterns and human-in-the-loop workflows, making it a research-backed choice for orchestrating agent teams.
AgentGPT
AgentGPT — Assemble, configure, and deploy autonomous AI Agents in your browser.
Auto-GPT
Auto-GPT — An experimental open-source attempt to make GPT-4 fully autonomous.
babyagi
babyagi — An AI-powered task management system.
Devin
Devin — An autonomous AI software engineer by Cognition Labs.
GPT Engineer
GPT Engineer — Specify what you want it to build, the AI asks for clarification, and then builds it.
GPT Pilot
GPT Pilot — Dev tool that writes scalable apps from scratch while the developer oversees the implementation.
GPT Prompt Engineer
GPT Prompt Engineer — Automated prompt engineering. It generates, tests, and ranks prompts to find the best ones.
MetaGPT
MetaGPT — The Multi-Agent Framework: Given one line requirement, return PRD, design, tasks, repo.
AgentMail
AgentMail — An email API built for AI agents, letting them create inboxes and send, receive, and organize email.
Claude Code
Claude Code — Anthropic’s agentic coding tool that lives in your terminal and helps you turn ideas into code.
Davika
Davika — An agentic AI software engineer.
Gemini CLI
Gemini CLI — An open-source AI agent that brings the power of Gemini directly into your terminal.
Mastra
Mastra — A TypeScript framework for building AI agents, workflows, and applications.
Moltbook
moltbook — A social network for AI agents.
OpenClaw
OpenClaw — A personal AI assistant you run on your own devices.
OpenCode
OpenCode — The open-source AI coding agent.
OpenHands
OpenHands — An autonomous agent designed to navigate the complexities of software engineering.
Openwork
Openwork — AI agents hire each other, complete work, verify outcomes, and earn tokens.
Sauna
Sauna — An AI assistant built for compounding context. It learns your taste, detects hidden patterns, augments your brain context and works proactively.
Agent Skills
Agent Skills — Open format and reference SDK for packaging reusable capabilities and expertise for AI agents.
Dorothy
Dorothy — An open-source desktop app to orchestrate multiple AI CLI agents simultaneously with automations and Kanban management.
Hermes Agent
Hermes Agent — A self-improving personal agent with memory, messaging integrations, and sandboxed tool execution.
Hive
Hive — An open-source multi-agent framework with auto-generated graphs, evolution loops, and MCP integration.
OpenAgents
OpenAgents — Open-source platform for building AI agent networks with multi-protocol support (WebSocket, gRPC, HTTP, MCP, A2A).
PraisonAI
PraisonAI — A framework for building multi-agent AI systems with workflows, tool integrations, and memory.