Neo4j Labs Model Context Protocol servers

Open-source Agent Operating System

One Page Agent.The browser-native workbench that lives in One Page.

self-healing and self-learning loop for coding agents

The most RAM efficient harness

Growing Expertise for Coding Agents — structured expertise files that accumulate over time, live in git, work with any agent

Headless knowledge base with bidirectional Markdown sync

An official Qdrant Model Context Protocol (MCP) server implementation

The agent that grows with you

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

An official set of skills to share, maintain and connect personal AI Agents.

Build and run agents you can see, understand and trust.

A lightweight, lightning-fast, in-process vector database

The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions

Context Engineering: Build Consistent, Accurate, Predictable AI Systems

Lightweight agent orchestration dev tool that lives in your repo

From Java Dev to AI Engineer: Spring AI Fast Track

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

An Orchestrate multiple coding agent desktop app

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

A proposed convention for the .agents/ directory to prevent context bloat and improve agent reasoning in complex codebases.