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?

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

An open protocol enabling communication and interoperability between opaque agentic applications.

Real-time automated accessibility testing inside the WordPress editor to help you find and fix WCAG compliance issues before publishing.

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 …

MCP server(s) for Aipolabs ACI.dev

Agent Communication Protocol

🎭 Stateful serverless framework for Rivet, Cloudflare Workers, Bun, and Node.js. Build AI agents, realtime apps, game servers, and more.

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…

AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ

Create state-machine-powered LLM agents using XState

Nosana Builders' Challenge: Agent 101

AgentKit is a framework for creating and orchestrating AI Agents, from single model inference calls to multi-agent systems which use tools.

MCP server for the planning and execution of AI-assisted development projects.

Rules and Knowledge to work better with agents such as Claude Code or Cursor

Agent S: an open agentic framework that uses computers like a human

Readymade evaluators for agent trajectories

Next Generation Agentic Proxy for AI Agents and MCP servers

TypeScript Agentic AI Library specialized for LLM Function Calling enhanced by compiler skills.

AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.

An implementation of iterative deep research using the OpenAI Agents SDK

AST-based code execution engine for agents, enabling stop/start workflows, tool-level state management, and enhanced observability.

Multi-agent orchestration for Claude Code with 99.3% token reduction, self-improving agents, and automatic claim verification. Build complex projects 10x faster.

Cryptocurrency trades aggregator

A lightweight library for building Multimodal Agents. Use it to give LLMs superpowers like memory, knowledge, tools and reasoning.

A full-featured, hackable Next.js AI chatbot built by Vercel