AI Agents
AI agents go beyond chat — they autonomously plan tasks, use tools, make decisions, and execute multi-step workflows. From coding agents like Devin and Claude Code to research agents and automation frameworks like AutoGPT and CrewAI.
yicoclaw - AI Agent Workspace
LanceDB implementation of RAG interfaces for vibe-agent-toolkit
A shared AI Agent for Teams
Generate AI agent skills from npm package documentation
Shennian — AI Agent Mobile Console CLI
Ralph TUI - AI Agent Loop Orchestrator
AI agent command firewall with Telegram-based human approval
OpenHiru — AI agent controlled via Telegram
Create BubbleLab AI agent applications with one command
Compact, language-agnostic codebase mapper for LLM token efficiency.
Blade AI Agent SDK
The CDK Construct Library for Amazon Bedrock
AI agent orchestration platform
AgentDB v3 - Intelligent agentic vector database with RVF native format, RuVector-powered graph DB, Cypher queries, ACID persistence. 150x faster than SQLite with self-learning GNN, 6 cognitive memory patterns, semantic routing, COW branching, sparse/part
AI Agent Task Management Dashboard
Teams-first Multi-agent orchestration for Claude Code
Mobile-Agent: The Powerful GUI Agent Family
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Zero-Config Code Flow for Claude code & Codex
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Knowledge Engine for AI Agent Memory in 6 lines of code
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
Pocket Flow: Codebase to Tutorial
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
TradingAgents: Multi-Agents LLM Financial Trading Framework
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
Agent S: an open agentic framework that uses computers like a human
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
Open-source AI coworker, with memory
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
Open source AI coding agent. Designed for large projects and real world tasks.
The agent that grows with you
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
A programming framework for agentic AI
12 Lessons to Get Started Building AI Agents
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Universal memory layer for AI Agents
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
Build resilient language agents as graphs.
The agent engineering platform
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.
🎭 211 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 16 种工具，覆盖工程/设计/营销/金融等 18 个部门。含 46 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）
Clone any website with one command using AI coding agents
Make Any Website & Tool Your CLI. A universal CLI Hub and AI-native runtime. Transform any website, Electron app, or local binary into a standardized command-line interface. Built for AI Agents to discover, learn, and execute tools seamlessly via a unified AGENT.md integration.
Vane is an AI-powered answering engine.
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
AI generates natively editable PPTX from any document — real PowerPoint shapes, not images — no design skills needed
This repository contains the Hugging Face Agents Course.
"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Autonomous AI development loop for Claude Code with intelligent exit detection
Build AI Agents, Visually
280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social media, DevOps, and document processing. The largest open-source n8n template collection.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
omo; the best agent harness - previously oh-my-opencode
Data infrastructure for AI
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, a
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Open-source context retrieval layer for AI agents
FinRobot: An Open-Source AI Agent Platform for Financial Analysis using LLMs 🚀 🚀 🚀
Build, run, manage agentic software at scale.
A generative speech model for daily dialogue.
Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)
Autonomous novel writing AI Agent — agents write, audit, and revise novels with human review gates
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Bindu: Turn any AI agent into a living microservice - interoperable, observable, composable.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
👾 Open source implementation of the ChatGPT Code Interpreter
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
Harness LLMs with Multi-Agent Programming
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) i
What are AI Agents?
AI agents are systems that can autonomously plan, reason, use tools, and execute multi-step tasks. Unlike chatbots that respond to single prompts, agents maintain state across steps, make decisions about which tools to invoke, and can recover from failures. The agent landscape spans from coding agents (Devin, Claude Code, Aider) that write and debug software to research agents that synthesize information across sources, and general-purpose frameworks (LangGraph, CrewAI, AutoGen) for building custom agent systems.
How to Choose
Start with what the agent needs to DO, not what framework it uses. For coding tasks, evaluate code agents on codebase understanding (can it read your entire repo?), tool access (can it run tests, use git?), and autonomy level (does it need approval for every file change?). For custom agents, evaluate frameworks on their planning mechanism (ReAct vs. tree search vs. graph-based), tool integration depth, memory management, and how they handle errors in multi-step chains.
Key Capabilities to Evaluate
Common Patterns
Reason → Act → Observe → Repeat. The most common agent pattern, used by LangChain agents and most coding assistants.
Generate a full plan upfront, then execute steps sequentially. Better for complex, predictable tasks.
Multiple specialized agents coordinated by a supervisor. Used by CrewAI, AutoGen, and complex enterprise workflows.
LLM decides which tool to call in each iteration until the task is complete. The pattern behind Claude's tool use and OpenAI function calling.
What to Watch Out For
Top Capabilities
Browse all →Analyzes selected code or entire files and generates natural language explanations of what the code does, how it works, and why certain patterns were chosen. The feature can produce documentation in multiple formats (docstrings, comments, markdown) and supports various documentation styles (JSDoc, Sphinx, etc.). Developers can request explanations at different levels of detail (high-level overview, line-by-line breakdown, architectural context) through the chat interface, with responses appearing as formatted text or code comments.
Translates non-English speech directly to English text using the same Transformer encoder-decoder architecture by prepending a 'translate' task token during decoding, bypassing explicit transcription. The AudioEncoder processes mel spectrograms identically to transcription, but the TextDecoder generates English tokens directly from audio embeddings. This end-to-end approach avoids cascading errors from intermediate transcription-then-translation pipelines and enables language-agnostic audio understanding.
Detects the spoken language in audio by analyzing the AudioEncoder embeddings and using the TextDecoder to predict a language token before generating transcription text. Language detection is implicit in the multitask training; the model learns to identify language from acoustic features without a separate classification head. Supports 99 languages with varying confidence based on training data representation (English: 65% of training data, others: 0.1-2%).
Maintains conversation history within a single chat session, allowing developers to ask follow-up questions, request refinements, and build on previous responses without re-providing context. The extension manages conversation state (messages, responses, context) and sends the full conversation history to ChatGPT's API with each request, enabling contextual understanding of refinement requests like 'make it faster' or 'add error handling'.
Generates new code snippets based on natural language descriptions by sending the user's intent and current editor selection context to OpenAI's API, then inserting the generated code at the cursor position or displaying it in the sidebar. The extension reads the active editor's selected text to provide code context, enabling the model to generate syntactically appropriate code for the detected language. Generation is triggered via keyboard shortcut (Ctrl+Alt+G), command palette, or toolbar button.
Generates docstrings, comments, and API documentation for functions, classes, and modules by analyzing code structure and semantics using GPT-4o. The extension detects function signatures, parameter types, and return types, then generates documentation in multiple formats (JSDoc, Python docstrings, Javadoc, etc.) matching the language and project conventions. Generated docs are inserted inline with proper indentation and formatting.
Analyzes staged or modified code changes in the current Git repository and generates descriptive commit messages using the configured AI provider. The feature integrates with VS Code's Git context to identify changed files and diffs, then sends this information to the AI model to produce commit messages following conventional commit formats or project-specific conventions. This automation reduces the cognitive load of writing commit messages while maintaining code quality and repository history clarity.
Offers a freemium pricing structure where basic problem detection and explanations are available for free, with premium features (likely advanced fix generation, priority support, or higher API quotas) available through paid subscription. The free tier includes GNN-based problem detection and LLM-powered explanations using Metabob's default backend, while premium tiers likely unlock OpenAI ChatGPT integration, higher analysis quotas, or team features. Pricing details are not publicly documented in the marketplace listing.
Browse Other Types
Foundation models, fine-tunes, and specialized AI models
MCP ServersModel Context Protocol tools and integrations
RepositoriesOpen-source AI projects on GitHub
APIsProgrammatic endpoints for AI capabilities
ExtensionsBrowser and IDE extensions powered by AI
WorkflowsAutomation sequences and AI pipelines
View all 14 types →Frequently Asked Questions
What is the difference between an AI agent and a chatbot?
A chatbot responds to individual messages. An AI agent can autonomously plan multi-step tasks, use external tools, maintain memory across interactions, and execute actions without human intervention for each step. Agents have a loop: observe → think → act → observe results → repeat until done.
Which AI coding agent is best for large codebases?
For large codebases, look for agents that index your entire repository (not just the current file), support multi-file edits, and can run tests to verify their changes. Cursor, Claude Code, and Aider are leading options, each with different approaches to codebase understanding.
How do multi-agent systems work?
Multi-agent systems use multiple specialized AI agents coordinated by an orchestrator. Each agent has a specific role (researcher, coder, reviewer) and they communicate through shared state or message passing. Frameworks like CrewAI, AutoGen, and LangGraph provide different coordination patterns.