Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Your AI agent, fluent in Australian tax. MCP server with cited answers from 34,500+ ATO documents, the income tax and GST Acts and 4,900+ rulings, plus deduction, depreciation, BAS and audit-risk tools that know your tax profile.

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

VibeSkills is a general-purpose Skill that automatically routes local Skills and intelligently orchestrates harness workflows.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.

An Open, Structured, and Standard Registry for MCP Servers and Packages.

Model Context Protocol server for Firefox DevTools - enables AI assistants to inspect and control Firefox browser through the Remote Debugging Protocol

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.

An official Qdrant Model Context Protocol (MCP) server implementation

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d

Extract public Spotify data — tracks, albums, artists, playlists, podcasts & lyrics — without the official API. Sync + async, typed models, one dependency.

Prismer Cloud

🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.

Advanced GitLab MCP server

A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

MCP server for Adobe Premiere Pro with 288 core AI video editing tools and a capability-aware UXP bridge for supported Premiere workflows.