Discover Production-Ready AI Agents
Web Manus indexes 169+ open-source AI agents built with LangChain, CrewAI, and AutoGen. Find the perfect agent for your project in seconds.
Not sure where to start?
Describe your project, and our AI will recommend the best agents
What is Web Manus?
Web Manus is the discovery platform for AI agents. We index production-ready agent examples from the open-source community, making it simple to find exactly what you need. Think of it like a search engine, but for AI agents that actually work.
The AI landscape moves fast. Every week, new frameworks emerge. LangChain, CrewAI, AutoGen, LlamaIndex, Phidata—the list keeps growing. Each one promises to solve different problems. But here is the challenge: how do you know which agent fits your project? Reading through hundreds of GitHub repositories wastes hours. Web Manus solves this problem.
We currently index 169+ agents across 12 categories. Each agent comes with real code you can run today. No theoretical examples. No placeholder functions. These are battle-tested implementations from developers who shipped actual products.
Why AI Agents Matter in 2025
AI agents represent the next evolution beyond chatbots. A chatbot answers questions. An agent takes action. It can browse the web, write code, analyze documents, send emails, and coordinate with other agents to complete complex tasks.
According to industry research, the AI agent market is projected to reach $47 billion by 2030. Companies like Anthropic, OpenAI, and Google are racing to build more capable foundation models. But models alone are not enough. You need the right architecture to put them to work.
That is where agent frameworks come in. LangChain pioneered the space with chains and tools. CrewAI introduced multi-agent collaboration. AutoGen from Microsoft brought conversation-based programming. LlamaIndex focused on RAG (Retrieval Augmented Generation). Each framework has strengths depending on your use case.
10x Productivity
Agents automate repetitive tasks that used to take hours. Code reviews, data analysis, research—done in minutes.
Production-Ready Code
Every agent in our index comes from real projects. Copy, customize, and deploy to your own infrastructure.
Open Source First
All indexed agents are open source. No vendor lock-in. Full control over your data and deployments.
Trending Agents
Most popular agents by GitHub stars
Ai Music Generator Agent
Generates custom music tracks from prompts, genre, mood, and instruments with an OpenAI-powered UI.
Default Tracing
Shows default tracing for OpenAI Agents SDK, capturing events and metadata for observability dashboards.
Execution Methods
Compares run_sync, run, and run_streamed execution modes for OpenAI Agents SDK with async vs sync.
Memory Operations
Demonstrates session memory CRUD (add, get, pop, clear) using OpenAI Agents SDK.
Product Review Agent
Structured product review agent that outputs pros/cons, sentiment, and recommendations using schemas.
Support Ticket Agent
Creates structured support tickets with priority, fields, and validation via schemas.
🎮 Agent X vs Agent O: Tic-Tac-Toe Game
An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on Agno Agent Fram
🎯 Tutorial 2: Structured Output Agent
Tutorial on structured outputs with Pydantic schemas for reliable JSON responses.
🎯 Tutorial 3: Structured Output Agent
Google ADK tutorial on structured outputs and schema validation for predictable responses.
📋 Tutorial 6: Callbacks
Explores Google ADK callbacks across lifecycle, LLM interaction, and tool execution hooks.
🔁 Tutorial 9.2: Loop Agents - Iterative Plan Refiner
Iterative loop agent that refines plans until stop conditions are met in multi-agent patterns.
Ai Movie Production Agent
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-mov
Browse by Category
Our agents span 12 categories. From RAG applications that answer questions about your documents, to coding assistants that write and review code, to research agents that scan the web for insights.
How to Find the Right Agent
Finding the right AI agent should take seconds, not hours. Web Manus provides three ways to discover exactly what you need:
Search by Keyword
Type what you want to build. 'PDF chatbot', 'code reviewer', 'email assistant'. Our search understands natural language.
Filter by Framework
Already using LangChain? Filter to see only LangChain agents. Same for CrewAI, AutoGen, LlamaIndex, and others.
Ask the AI Concierge
Describe your project in plain English. Our AI analyzes your requirements and recommends the best matching agents.
Popular Agent Frameworks
Not sure which framework to choose? Here is a quick overview of the most popular options in our index:
LangChain
50+ agentsThe most popular framework. Great for building chains of LLM calls with tools, memory, and retrieval. Best for general-purpose agents.
CrewAI
30+ agentsSpecializes in multi-agent systems. Define agents with roles, assign tasks, and let them collaborate. Best for complex workflows.
AutoGen
20+ agentsMicrosoft's framework for conversational agents. Agents communicate through messages. Best for dialogue-based applications.
LlamaIndex
25+ agentsPurpose-built for RAG applications. Excellent indexing, retrieval, and query capabilities. Best for document Q&A systems.
Real-World Use Cases
Our users build everything from internal tools to customer-facing products. Here are some popular patterns:
Customer Support Bots
RAG-powered chatbots that answer questions from your documentation. Reduce ticket volume by 40% or more.
Code Review Assistants
Agents that analyze pull requests, suggest improvements, and catch bugs before they reach production.
Market Research Agents
Automated research that scans news, analyzes competitors, and generates daily briefings.
Content Generation
Agents that draft blog posts, social media content, and marketing copy with your brand voice.
Getting Started is Simple
Every agent in our index links directly to its source code. No account required. No paywall. Just find an agent, click through to GitHub, clone the repo, and start customizing.
Most agents include setup instructions, environment variable templates, and example usage. Many work with both cloud APIs (OpenAI, Anthropic, Google) and local models (Ollama, vLLM) so you can choose based on your privacy and cost requirements.
What You Get With Every Agent
- Complete source code
- Setup instructions
- Environment templates
- Framework documentation
- LLM provider options
- Community support
Ready to Build Your Agent?
Explore our catalog of 169+ production-ready agents and start building today. No signup required.