Knowledge & Memory

Persistent cross-session memory for Claude Code and any MCP-compatible client.

MCP server for Biolink Model Toolkit

A Python MCP server for Qdrant memory storage and semantic search, compatible with Cursor-like MCP clients.

[DEPRECATED - use EchoVault] MCP Server for AI memory with PostgreSQL

Cross-agent memory handoff via MCP — agents pass the baton instead of re-exploring the repo

Empirical memory for AI agents — patterns learned from real executions, not hand-written rules. Workflow checkpointing, failure knowledge base, multi-agent coordination. Zero API keys required.

World-reference data (taxonomy, OBO terms, nutrition, observations, Wikidata alignment) MCP server and scion-sdk source adapters

MCP server for SwarmV: persistent vector memory for AI agents, limited to what the user may access.

Single-file, self-hosted semantic memory MCP server for AI coding agents

Contest calendar and rules MCP server: what is running, what is coming, and the rules

MCP server that gathers a repo's Markdown memory files into one searchable, stamped knowledge graph

PASM 认知内核的 MCP 服务器 —— 把 PASM 的记忆/情绪/动作/反馈能力暴露成标准 MCP 工具，挂进任意支持 MCP 的客户端（Claude Desktop / Cursor / VS Code / 自研 Agent）

Turn mathematical LaTeX papers into theorem dependency graphs for AI agents.

A stdio MCP server over mnimi: remember, recall, context, export, consolidate; one SQLite file, no server process beyond this one.

MCP server for Mnemosyne: an AI agent's memory as tools and resources.

An MCP server that maps your ML / GNN workflow as a node graph and records every experiment as a branching tree, while Codex or Claude Code works.

Meteor scatter planning between two stations: showers, radiant geometry, live counts

Event-sourced, branchable memory kernel and MCP server for multi-agent coding systems

Universal Architecture Knowledge Graph & Blueprint Model Context Protocol (MCP) server for full-stack codebases (Next.js, NestJS, Drizzle, PostgreSQL/MySQL).

MCP server giving Claude Code, Cursor, Codex and Windsurf permanent AST-powered code memory. 98.9% token reduction. 100% local.