Developer · Local MCP server
Memory for AI
Local codebase knowledge graph for AI agents - 162 languages, sub-ms queries, 99% fewer tokens.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.LonelyTraderBay/memory-for-ai- Version
- 0.11.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm, PyPI, MCP Bundle (.mcpb)
- Published
- 2026-09-18
- Updated
- 2026-09-18
- Publisher
- LonelyTraderBay (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/LonelyTraderBay) · how
- Website
- github.com/LonelyTraderBay/memory-for-ai/
- Repository
- github.com/LonelyTraderBay/memory-for-ai
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | memory-for-ai-mcp | 0.11.0 | stdio |
| PyPIruntime: uvx | memory-for-ai | 0.11.0 | stdio |
| MCP Bundle (.mcpb) | https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-darwin-amd64.mcpbSHA-256 checksum stated | 0.11.0 | stdio |
| MCP Bundle (.mcpb) | https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-darwin-arm64.mcpbSHA-256 checksum stated | 0.11.0 | stdio |
| MCP Bundle (.mcpb) | https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-linux-amd64-portable.mcpbSHA-256 checksum stated | 0.11.0 | stdio |
| MCP Bundle (.mcpb) | https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-linux-arm64-portable.mcpbSHA-256 checksum stated | 0.11.0 | stdio |
How to connect Memory for AI
Memory for AI runs locally from a Node.js package published to the npm registry: memory-for-ai-mcp version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y memory-for-ai-mcp@0.11.0.
Memory for AI runs locally from a Python package published to PyPI: memory-for-ai version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx memory-for-ai.
Memory for AI runs locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-darwin-amd64.mcpb version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.
Memory for AI runs locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-darwin-arm64.mcpb version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.
Memory for AI runs locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-linux-amd64-portable.mcpb version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.
Memory for AI runs locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/LonelyTraderBay/memory-for-ai/releases/download/v0.11.0/memory-for-ai-linux-arm64-portable.mcpb version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"memory-for-ai": {
"command": "npx",
"args": [
"-y",
"memory-for-ai-mcp@0.11.0"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| memoricProvenance-first database for teams and agents: every value carries sources, rules and coverage. | Remote · HTTPLive check: sign-in required |
| MemoroPersonal AI memory layer on your own computer. Read/write durable memory across MCP clients. | Local · stdio |
| MemoryShared, persistent memory for AI agents - works with Claude, Kiro, Cursor, or any MCP client. | Local · stdio |
| Memory FabricFile-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB. | Local · stdio |
| Memory FtsLong-term memory for Claude Code with SQLite FTS5 search and BM25 ranking. | Local · stdio |
| Memory Journal MCPDeveloper journal with knowledge graphs, relationships, Git context, and semantic search. | Local · stdio |
| Memory KernelLocal-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud. | Local · stdio |
| Memory MCPPersistent memory + git snapshots for Claude Code. Never lose context or code. | Local · stdio |