ai-agent
Interactive UI Components for MCP SDK for UI over MCP. Create next-gen UI experiences!
Build rich, dynamic user interfaces for your MCP applications with SDKs that bring UI to AI interactions.
any-agent is a Python library providing a single interface to different agent frameworks.
AI powered Kubernetes Assistant.
kubectl-ai acts as an intelligent interface, translating user intent into precise Kubernetes operations, making Kubernetes management more accessible and efficient.
Build Agents that Never Hallucinate. Deploy the most accurate RAG in the world in two lines of code.
The most accurate document search and store for building AI apps.
Related contents:
The AI IDE for prototype to production.
Kiro is an agentic IDE that helps you go from prototype to production with spec-driven development, agent hooks, and natural language coding assistance. Build faster with AI-powered features that understand your entire codebase, turn prompts into structured specs, and automate repetitive tasks.
Related contents:
Run a bunch of Claude Codes in parallel.
Each Claude gets an isolated workspace. See who’s working, see who’s stuck, and what’s changed.
Open Source AI coding assistant for planning, building, and fixing code. We're a superset of Roo, Cline, and our own features.
Detect agentic coding environments and AI editors.
Detect agentic coding environments and AI assistant tools. This library allows CLI tools and Node apps to detect when they're being executed by AI agents. This enables them to adapt by, for example, providing different output formats or logs.
An open-source, code-first Python or Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and is built for compatibility with other frameworks. ADK was designed to make agent development feel more like software development, to make it easier for developers to create, deploy, and orchestrate agentic architectures that range from simple tasks to complex workflows.
MCP server for interaction with the Bitwarden vault.
Model Context Protocol (MCP) server that enables interaction with the Bitwarden password manager vault via the MCP protocol. The server allows AI models to securely communicate with a user's Bitwarden vault through defined tool interfaces.
Related contents:
Orchestrate AI Coding Agents. Kanban board to manage your AI coding agents.
AI coding agents are increasingly writing the world's code and human engineers now spend the majority of their time planning, reviewing, and orchestrating tasks. Vibe Kanban streamlines this process.
The Open-Source Agentic Browser. Your Browser, Reimagined.
We believe browsers must be open source, not owned by search or ad companies. And the future is AI agents automating your work locally and securely. We're building the best browser for that future.
Model Context Protocolfor the Browser
Browser-based Model Context Protocol (MCP) implementation that enables AI assistants to interact with web applications through standardized MCP tools.
Today's AI automation is like using a robot to read your screen and click buttons. MCP-B gives AI direct access to your website's functions instead.
Build Real-Time Knowledge Graphs for AI Agents.
Graphiti is a Python framework for building temporally-aware knowledge graphs designed for AI agents. It enables real-time incremental updates to knowledge graphs without batch recomputation, making it suitable for dynamic environments where relationships and information evolve over time.
The OpenCLI specification (OCS) defines a standard, platform and language agnostic interface to CLI applications which allows both humans and computers to understand how a CLI tool should be invoked without access to source code or documentation.
An OpenCLI Description can be used by documentation software to display usage of a tool, or code generation tools to create clients for interoping with a CLI tool.
Related contents:
Markdown‑native Task Manager & Kanban visualizer for any Git repository.
A tool for managing project collaboration between humans and AI Agents in a git ecosystem.
Backlog.md turns any folder with a Git repo into a self‑contained project board powered by plain Markdown files and a zero‑config CLI.
Amp is an agentic coding tool engineered to maximize what’s possible with today’s frontier models—autonomous reasoning, comprehensive code editing, and complex task execution.
Related content:
Give Cursor Agent an AI Team and Advanced Skills
Testing WASM-powered AI agents.
This Blueprint demonstrates how to run AI agents directly in the browser using WebAssembly (WASM) through Pyodide and the OpenAI Agents Python SDK. Experience the power of Python-based AI agents without external dependencies – agent code runs directly in your web browser.
Related contents:
Easily launch a Claude Code session that is connected to a swarm of Claude Code Agents.
Claude Swarm orchestrates multiple Claude Code instances as a collaborative AI development team. It enables running AI agents with specialized roles, tools, and directory contexts, communicating via MCP (Model Context Protocol) in a tree-like hierarchy. Define your swarm topology in simple YAML and let Claude instances delegate tasks through connected instances. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.
Related contents:
An open-source implementation of the AlphaEvolve system described in the Google DeepMind paper "AlphaEvolve: A coding agent for scientific and algorithmic discovery" (2025).
A Model Context Protocol (MCP) server for accessing the OpenTofu Registry. This server allows language model assistants to search for and retrieve information about OpenTofu providers, modules, resources, and data sources.
Improve your AI infrastructure - AI memory engine. Memory for AI Agents in 5 lines of code.
Build dynamic memory for Agents and replace RAG using scalable, modular ECL (Extract, Cognify, Load) pipelines.
Build agents that scale with a zero-cost abstraction.
Pickaxe is a simple Typescript library for building AI agents that are fault-tolerant and scalable. It handles the complexities of durable execution, queueing and scheduling, allowing you to focus on writing core business logic. It is not a framework.
Agent User Interaction Protocol.
AG-UI is a lightweight, event-based protocol that standardizes how AI agents connect to front-end applications. Built for simplicity and flexibility, it enables seamless integration between your AI agents and user interfaces.
AG-UI standardizes how front-end applications connect to AI agents through an open protocol. Think of it as a universal translator for AI-driven systems- no matter what language an agent speaks: AG-UI ensures fluent communication.
Your browser, with AI superpowers 🚀. Nxtscape is an open-source agentic browser.
🌐 Nxtscape is an open-source agentic browser that runs AI agents locally. Your privacy-first alternative to Arc, Dia, and Perplexity Comet.
simplify and secure MCP servers. ToolHive makes deploying MCP servers easy, secure and fun.
Run any Model Context Protocol (MCP) server — securely, instantly, anywhere.
ToolHive is the easiest way to discover, deploy, and manage MCP servers. Launch any MCP server in a locked-down container with a single command. No manual setup, no security headaches, no runtime hassles.
EnrichMCP is a Python framework that helps AI agents understand and navigate your data. Built on MCP (Model Context Protocol), it adds a semantic layer that turns your data model into typed, discoverable tools - like an ORM for AI.
The Data Layer for Agentic Enrichment and ML Features. The Virtual Feature Store. Turn your existing data infrastructure into a feature store.
Featureform is a virtual feature store. It enables data scientists to define, manage, and serve their ML model's features. Featureform sits atop your existing infrastructure and orchestrates it to work like a traditional feature store. By using Featureform, a data science team can solve the following organizational problems:
The AI Shell. AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models.
A comprehensive coding agent that integrates AI capabilities with your development environment.
An ever growing list of open source MCP servers 📡 📁 🚀
Explore thousands of MCP servers. And connect to them in a single function call.
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Container Use lets each of your coding agents have their own containerized environment. Go from babysitting one agent at a time to enabling multiple agents to work safely and independently with your preferred stack.
Unified MCP Server Implementation.
A comprehensive Model Context Protocol (MCP) server implementing the latest MCP 2025-03-26 specification. Demonstrates MCP capabilities including tools, resources, prompts, roots, and enhanced sampling with model preferences. Features HackerNews and GitHub API integrations with AI-powered analysis through advanced MCP sampling.
easy secure execution of untrusted user/ai code.
Run untrusted code with VM-level isolation and lightning-fast startup. Built for AI agents, developers, and anyone who needs to execute code safely without compromising on speed or security.
The fast, Pythonic way to build MCP servers and clients.
The Model Context Protocol (MCP) is a new, standardized way to provide context and tools to your LLMs, and FastMCP makes building MCP servers and clients simple and intuitive. Create tools, expose resources, define prompts, and more with clean, Pythonic code.
Related contents:
CLI for running large numbers of coding agents in parallel with git worktrees
Related contents:
Manage multiple AI agents like Claude Code, Aider, Codex, and Amp. 10x your productivity.
Related contents:
A lightweight, zero-overhead implementation of the Model Context Protocol (MCP) server in pure Bash.
Why? Most MCP servers are just API wrappers with schema conversion. This implementation provides a zero-overhead alternative to Node.js, Python, or other heavy runtimes.
Run MCPs without the complexity ⚡️
OneMCP is an app that lets you run any MCP without the complexity of downloading repos, reading docs, or setting up servers.
Related contents:
Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.
🦉 OWL is a cutting-edge framework for multi-agent collaboration that pushes the boundaries of task automation, built on top of the CAMEL-AI Framework.
Turn Apps Into Agent-Ready Knowledge. Empower Agents with Deep Knowledge About Their Users. Give Users the Experience They Deserve
Airweave is a tool that lets agents semantically search any app. It's MCP compatible and seamlessly connects any app, database, or API, to transform their contents into agent-ready knowledge.
Airweave simplifies the process of making information retrievable for your agent. Whether you have structured or unstructured data, Airweave helps you break it into processable entities, store the data and make it retrievable through REST and MCP endpoints.
a Hugging Face Space by smolagents.
open source agent taking control of a computer desktop.
Related contents:
GitHub's official MCP Server.
The GitHub MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with GitHub APIs, enabling advanced automation and interaction capabilities for developers and tools.
Related contents:
Suna by Kortix – is a generalist AI Agent that acts on your behalf.
Suna is a fully open source AI assistant that helps you accomplish real-world tasks with ease. Through natural conversation, Suna becomes your digital companion for research, data analysis, and everyday challenges—combining powerful capabilities with an intuitive interface that understands what you need and delivers results.
MCP Integrationfor AI Applications
The best way to get access to production-ready MCP servers at scale.
Klavis AI makes it effortless to connect to production-ready MCP servers & clients at scale. Integrate with your AI application in under a minute, and scale to millions of users using our open-source infrastructure, hosted servers, and multi-platform clients!
integrate LLM with any tool. ACI: Open-Source Infra to Power Unified MCP Servers.
ACI.dev is the open-source infrastructure layer for AI-agent tool-use. It gives your agents intent-aware access to 600+ tools with multi-tenant auth, granular permissions, and dynamic tool discovery—exposed as either direct function calls or through a Unified Model-Context-Protocol (MCP) server.
ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP server.
The PM for your AI agent. An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
Taskmaster is your AI's personal project manager. Organize, research, expand, prioritize, and ship tasks effortlessly. Enjoy permanent context, zero drift & instant clarity. It's free, open-source & API-friendly. Let's vibe productively.
Terminal Commands and File Editing for Claude.
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities.
MCP server for understanding AWS spend.
An MCP server for getting AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic's MCP (Model Control Protocol).
MCP Server to fetch costs and usage data from your Vantage account.
Use natural language to explore your organization’s cloud costs via MCP clients, like Claude, Cursor, and others. Ask questions about your organization's previous and current cloud cost spend, cost tagging, provider integrations, and more.
An MCP server that autonomously evaluates web applications.
Browser Agents to vibe-test your web app. Let browser agents vibe-test your vibe-coding.
10x your vibe coding by giving your coding agent a browser agent that can vibe-test web applications via MCP.
Transparent AI, Rooted in Research, Open to All. The Open Source Deep Researcher Tool. AI-Powered Online Data Information Synthesis Assistant.
CleverBee is a powerful Python-based research assistant agent using Large Language Models (LLMs) like Claude and Gemini, Playwright for web browsing, and Chainlit for an interactive UI. It performs research assistance by browsing the web, extracting content (HTML), cleaning it, and synthesizing findings based on user research topics.
AI-Powered, Non-Intrusive Terminal Assistant
TmuxAI is a non-intrusive terminal assistant that works alongside you in a tmux window. TmuxAI's design philosophy mirrors the way humans collaborate at the terminal. Just as a colleague sitting next to you, TmuxAI observes your screen, understand context from what's visible, and helps accordingly.
Open source, AI-native testing framework for web apps.
End-to-end testing framework powered by visual AI agents that see your interface and adapt to any changes in it.
macOS & Linux Containers for Computer-Use AI Agents on Apple Silicon. Run Docker Containers for Computer-Use AI Agents on Apple Silicon.
TL;DR: c/ua (pronounced "koo-ah", short for Computer-Use Agent) is a framework that enables AI agents to control full operating systems within high-performance, lightweight virtual containers. It delivers up to 97% native speed on Apple Silicon and works with any vision language models.
Open-Source Browser Agent for autonomously performing complex tasks on the web
AI-powered multi-agent builder. Let AI build multi-agent systems for you Build with Agents SDK. Connect MCP tools. Open-source.
AI Autonomous Coding Agent for VS Code.
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Related contents: