加载中…
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Local Memory 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 73/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Local Memory 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y @studiomeyer/local-memory-mcp@2.4.3运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-08-09T03:33:19.381111Z",
"publishedAt": "2026-08-09T03:33:19.381111Z",
"statusChangedAt": "2026-08-09T03:33:19.381111Z"
}
},
"server": {
"name": "io.github.studiomeyer-io/local-memory-mcp",
"title": "Local Memory",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "2.4.3",
"packages": [
{
"version": "2.4.3",
"transport": {
"type": "stdio"
},
"identifier": "@studiomeyer/local-memory-mcp",
"registryType": "npm",
"environmentVariables": [
{
"name": "MEMORY_DB_PATH",
"format": "string",
"description": "Custom path for the SQLite database file"
},
{
"name": "MEMORY_EMBED_DISABLED",
"format": "string",
"description": "Disable the local embedding pipeline (forces FTS5-only search). Useful in restricted networks where the model can't be downloaded."
},
{
"name": "MEMORY_EMBED_MODEL",
"format": "string",
"description": "Override the embedding model id (defaults to Xenova/multilingual-e5-small)."
},
{
"name": "MEMORY_EMBED_CACHE_DIR",
"format": "string",
"description": "Override the Transformers.js cache directory (defaults to the OS data dir)."
}
]
}
],
"repository": {
"url": "https://github.com/studiomeyer-io/local-memory-mcp",
"source": "github"
},
"description": "Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys."
}
}