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.
Browser-based IDE + AI Agent — builds, runs, and deploys full apps from a description, 50+ languages supported.
Anthropic's terminal coding agent — file ops, git, MCP servers, extended thinking, slash commands.
Autonomous AI coding agent with file and terminal control.
Codeium's AI code editor — Cascade agentic flows, Supercomplete, inline commands, generous free tier.
Autonomous AI software engineer — full dev environment, end-to-end engineering, team integration.
AI full-stack web dev agent — prompt to deploy, in-browser Node.js, React/Next.js, instant deploy.
AI pair programming in terminal — git-aware, multi-file editing, auto-commits, voice coding.
AI junior developer — turns GitHub issues into pull requests automatically with full codebase context.
AWS AI coding assistant — code generation, AWS expertise, security scanning, code transformation agent.
Autonomous AI coding assistant for VS Code — reads, edits, runs commands with human-in-the-loop approval.
OpenAI's conversational AI for text, code, and analysis
Anthropic's AI with long-context and careful reasoning
AI agent for Obsidian knowledge vault.
Microsoft's AI agent for biomedical research.
Google's multimodal AI integrated with Google services
Stanford research agent that writes Wikipedia-quality articles.
AWS managed AI agents — action groups, knowledge bases, guardrails, multi-step orchestration.
Observability platform for AI agent debugging.
Princeton's GitHub issue solver — navigates code, edits files, runs tests, submits patches.
Self-hosted AI coding agent with privacy focus.
Open-source AI software engineer — writes code, runs tests, fixes bugs in sandboxed environment.
Natural language computer interface — runs local code to accomplish tasks, like local Code Interpreter.
Open-source AI personal assistant for your knowledge.
Personal AI assistant in terminal — code execution, file manipulation, web browsing, self-correcting.
Autonomous agent for comprehensive research reports.
AI agent that generates entire codebases from prompts — file structure, code, project setup.
Agent for accurate API invocation with reduced hallucination.
Block's autonomous terminal coding agent — MCP support, extensible toolkits, full shell access.
Open-source AI agent for financial analysis.
Agent that uses executable code as actions.
AI agent with chemistry tools for synthesis planning.
AI task management agent with autonomous execution.
Autonomous AI agent — chains LLM thoughts for goals with web browsing, code execution, self-prompting.
Open-source low-code with AI for internal tools.
AI-optimized search agent for LLM applications.
Self-hosted AI coding agent with full privacy.
AI code review agent for pull requests.
AI agent that builds and deploys full applications — IDE, hosting, databases, natural language.
AI PR review — auto descriptions, code review, improvement suggestions, open source by Qodo.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Enterprise AI agent platform for company knowledge.
Autonomous AI software engineer for full dev workflows.
AI agent that generates production code from specs.
Open-source AI coding agent as a VS Code fork.
AI coding assistant with full codebase context — autocomplete, chat, inline edits via code graph.
Advanced AI research agent with deep web search.
AI assistant integrated into Notion workspace.
AI agent for accelerated software development.
Platform for deploying conversational AI agents.
AI agent for automated systematic literature reviews.
AI platform for sales and marketing content automation.
GitHub's AI dev environment from issues to code.
AI coding agent with full codebase context from Sourcegraph.
AI project management assistant in ClickUp.
AI coding agent for professional software teams.
AI-powered app automation platform.
AI-powered E2E test automation with self-healing locators.
AI noise cancellation with meeting transcription.
AI-augmented test automation for web, API, mobile, and desktop.
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration
Codex is a coding agent that works with you everywhere you code — included in ChatGPT Plus, Pro, Business, Edu, and Enterprise plans.
Revolutionize Kubernetes management with AI-driven diagnostics, security analysis, and SRE...
Streamline business verification and fraud detection with AI-powered...
CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。
Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.
Revolutionize call management with AI-powered answering and workflow...
Streamline autonomous system development, testing, and...
Turn conversations into project plans. Gantta connects your AI assistant to a full project management backend — plan projects, manage tasks, chase actions, and generate reports, all through natural language. ### What you can do - **Create project plans** — Describe your project in plain language a
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.
Deploy human-like AI voice agents in just 17...
Revolutionize customer interactions with AI-powered, scalable voice...
Boost macOS productivity with AI-powered automation and...
Revolutionizes insurance brokerage with AI-powered automation and seamless...
Maximize efficiency with AI-powered form automation and...
AI-driven agents for instant, customizable business insights and...
Revolutionize software development with AI-driven coding...
AI-powered support automation platform that connects your entire tech stack to answer questions, automate repetitive support tasks, and build solutions to...
Streamline research, integrate data, generate tailored reports, enhance...
Search Enji’s blog, Q&A, and help center to find grounded, source-backed answers to small-business marketing questions. Generate customer personas, brand voice summaries, and tailored social and blog ideas to plan content faster. Access free resources and tools to stay consistent and confident in yo
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
The agent that grows with you
🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Runs on Claude Code / Codex / Cursor / Gemini
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Open Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands. Features inline autocomplete, browser automation, automated refactoring, and custom modes for planning, coding, and debugging. Supports 500+ AI models including Claude (Anthropic), Gem
AI assistant for e-commerce sales...
Create lifelike AI voice agents, deploy anywhere, analyze...
Revolutionize autonomous system management with global, secure...
AI-driven phone agent offering human-like, multilingual customer...
Build your AI Second Brain with a team of AI agents and multi-agent...
Revolutionize AI interactions with personalized, long-term memory...
Autonomously resolves customer inquiries with AI-driven...
Revolutionize communication with human-like, 24/7 AI voice...
Jamie is an AI assistant that generates high-quality meeting summaries in...
Revolutionize communication with lifelike, customizable AI...
Automates 70% of customer tickets with 99.8%...
Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
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
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.
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 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.
Cody utilizes a context-aware engine that analyzes the current file and project structure to provide relevant code completions. It integrates with the Visual Studio Code API to access the Abstract Syntax Tree (AST) of the code, allowing it to suggest completions that are semantically relevant to the context, rather than relying solely on keyword matching. This approach ensures that the suggestions are not only syntactically correct but also contextually appropriate, enhancing developer productivity.
Converts natural language prompts into executable full-stack web applications by invoking an AI agent that generates React/Next.js frontend code, Node.js backend logic, and database schemas. The agent runs code in-browser via WebContainers to validate syntax and functionality before deployment, iterating on the generated code based on execution feedback. Token consumption scales with project complexity (larger codebases consume more tokens per iteration), and the agent supports design system imports from Figma and GitHub to accelerate UI generation.
Provides six model variants (tiny, base, small, medium, large, turbo) with parameter counts ranging from 39M to 1550M, enabling developers to choose optimal speed-accuracy tradeoffs. Tiny model runs at ~10x speed with 1GB VRAM; large model runs at 1x speed with 10GB VRAM. English-only variants (tiny.en, base.en, small.en) provide higher English accuracy by removing multilingual capacity. Turbo model (809M params) offers 8x speedup over large with minimal accuracy loss but lacks translation support.
Translates non-English speech directly to English text by using a task-specific token in the TextDecoder that signals translation mode, bypassing the need for intermediate transcription-then-translation pipelines. The AudioEncoder processes mel spectrograms identically to transcription, but the decoder generates English tokens directly from audio embeddings, reducing latency and error propagation compared to cascaded systems.
Transcribes audio in 98 languages to text in the original language using a unified Transformer sequence-to-sequence architecture with a shared AudioEncoder that processes mel spectrograms into language-agnostic embeddings, then a TextDecoder that generates tokens autoregressively. The system handles variable-length audio by padding or trimming to 30-second segments and uses task-specific tokens to signal transcription mode, enabling a single model to handle multiple languages without language-specific branches.
Detects the spoken language in audio by processing mel spectrograms through the AudioEncoder and using a language classification head that outputs probability distributions over 98 supported languages. The model leverages 680K hours of multilingual training data to recognize language characteristics from acoustic features alone, without requiring transcription. Language detection occurs as a preliminary step in the transcription pipeline and can be called independently via the language detection task token.
W&B Personal tier (free) and Enterprise tier support self-hosted deployment via Docker, enabling on-premise installation for teams with data residency or security requirements. Self-hosted instances run independently from W&B cloud, with optional integration to W&B cloud for cross-instance features. Supports custom domain configuration, HTTPS, and integration with corporate identity providers (LDAP, SAML, OAuth).
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 19 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.