Knowledge & Memory

A Model Context Protocol server for persistent project-specific AI agent context.

A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows.

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

Universal RAG Memory MCP Server for AI assistants

Structured thinking + steel-manning verification for AI agents. Backed by 43+ papers.

Universal AI Agent Skills: Docker 3-Tier Workflow, Enterprise Production Architecture (NGINX, Cloudflare, Log Rotation), Git Team Workflow, AI API Gateway (9Router & LLM Routing), Oracle External Brain Lifecycle (~/ψ Vault), and Maymint Companion Soul & M

All-in-one MCP server: GitHub, Git, Slack, web fetch, memory, and filesystem. Agent Mode opt-in.

NWron memory MCP server (stdio) — persistent memory for coding agents. Extracts facts and embeds them locally (Voyage), stores them through the NWron API.

Local-first hybrid code search engine — 42 adapters, BM25 + vector + rerank, binary doc/image indexing, lazy background mode, MCP server

MCP server that gives GitHub Copilot CLI persistent long-term memory via local semantic vector search. Install: npx -y ghcp-cli-vector-memory-mcp

Cross-session memory for pi-coding-agent (pi-mono). A thin client for the local claude-mem worker: records tool activity, injects relevant past context, and registers a memory_recall search tool. Share memory across pi, Claude Code, Cursor, Codex and Open

Susan shows you what every Claude Code and Codex session on your machine is working through, keeps the decisions after the transcript is deleted, and answers ChatGPT web and Claude web over MCP.

MCP server for Redis diagnostics — analyze memory usage, slowlog, client connections, and keyspace health with AI-powered recommendations

DevsMind — Team AI Brain

AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions

Autonomous AI agent memory system with CLAUDE.md protocol enforcement

Ask your own documents with citations, plus durable memory for agents. Safe by default.

UK planning application data for AI agents: search, geo-query and fetch applications.

AI agent skill that turns any topic into a single-file interactive HTML explainer, with algorithmically laid-out architecture diagrams. Installs into Codex, Claude Code, Cursor rules, and generic AI CLIs.

AI agent with persistent memory, heartbeat check-ins, and a knowledge vault