by AdelElo13
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
npm:neuromcp · local package164/wkpublished 22 d ago
Storage, memory and knowledge management for agents.
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
An agent runner for apps that act on a customer's accounts: one scheduled pass per connected account, per-account caps, an approval step, an undo window and a receipt written before any send. Bring your own model.
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 38 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
The runtime layer for Agentic AI. 121 MCP tools: persistent memory, autonomous agents, vault storage, scheduled workflows, DeFi on Base (base_mcp_*), Robinhood Chain tokenized stocks and arbitrary crypto with V3/V4 smart routing (rh_*), live market data,
Local repo context for coding assistants with semantic search and graph relationships.
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
Cloudflare-hosted MCP server for code indexing, retrieval, and assistant memory with a direct remote MCP endpoint and local stdio bridge.
Persistent, shared memory for AI agents — facts, checkpoints, semantic search.
Render an AI agent's plans as visual MDX pages instead of walls of text
Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
Local memory layer for AI agents — coding assistants over MCP, game NPCs over REST
Mail MCP: IMAP/SMTP, Zimbra, Apple Mail, Microsoft and Mailtrap for Codex and Claude
Local multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.
Model Context Protocol server for Microsoft To Do (via Microsoft Graph).
Your Obsidian vault as private, searchable memory for Claude, Cursor, Hermes and any MCP client
Saves AI coding-agent context by giving exact code instead of whole files, from a local graph.
MCP server that gives coding agents persistent project understanding via a knowledge graph
AI Engineering Governance MCP Server - Session memory, knowledge system, feature registry, code intelligence, rule enforcement, tiered tooling (12 free / 73 total), 56 workflow commands, 11 agents, 20+ patterns
Agent-agnostic memory backend that preserves continuity between humans and AI over time.
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.