Find features you built in other projects, see how they fit this one, and reuse them.
Zero-dependency stdio MCP server for Thredz — long-term memory (wiki recall, semantic/keyword search, upsert, reflection signals), durable goals & tasks, and agent-to-agent messaging over the Thredz R
MCP server for Kerabie: lets Claude, Cursor and other MCP clients work with your conversations, tickets, contacts, campaigns, knowledge base, analytics and AI tools
Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.
Local long-term memory for terminal coding agents: blueprints, code anchors and distilled lessons in one JSON file, restoring project context across sessions.
Local-first memory for AI agents: facts with hash-chain provenance, verified recall.
Servidor MCP para almacenar y recuperar el historial de conversaciones de forma persistente mediante PostgreSQL.
Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.
Simple MCP RAG server using @modelcontextprotocol/sdk
Persistent memory storage and retrieval for AI agents through the hosted HeurChain MCP service.
SAP Fiori documentation indexing
MemDrive — an MCP server that gives LLMs persistent memory on local sync folders. Local filesystem backend, zero native dependencies.
Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes.
Persistent memory MCP server for AI coding agents
MCP distribution SDK. Build sales funnels, lead generation, booking, and quote apps on top of your MCP server. Event tracking, flows, widgets, knowledge base.
Read the MindForge engine over MCP: knowledge graph, project health, and audit log.
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
Local, privacy-focused RAG service for code search via MCP. https://linggen.dev
Semantic code knowledge graph for Kiro: fewer tool calls, instant symbol lookups, 100% local.
Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.
YATS — Yet Another Token Saver. One-command MCP server that indexes your codebase into a knowledge graph so AI agents (Claude, Cursor, Copilot) can search and navigate it without burning tokens.
BuilderForce Agent Memory — MCP transport. Exposes @seanhogg/builderforce-memory to any MCP client (Claude Agent SDK in-process, stdio, or HTTP) over a pluggable MemoryBackend, with token-saving fetch
Secure, fragment-based long-term memory for MCP-compatible AI agents.
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.
Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semantic bridge discovery and drift detection.
A second brain your AI assistants share: your notes, chats and mail, and memories kept as Markdown.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
MCP server for Naumu - access your knowledge graph from Claude Code, Cursor, and other AI coding agents
O(1) routing, semantic search, and quality-filtered demand-driven experiences over 800+ records.
CPU task-specific context preparation and explicitly saved local project notes through MCP.
Mimir long-term memory for OpenCode sessions
Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Official HTTP TypeScript & Node.js SDK for / ml (https://api.slashml.ai)
Persistent memory for Claude via weighted, interconnected knowledge nodes.
MCP server for persistent, semantic memory across AI sessions
Toàn bộ thư mục
RAG, đồ thị và bộ nhớ dài hạn cho agent. 2,638 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.