Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.
Use this profile to copy client config, check auth requirements, review tools and resources, and compare related MCP servers before adding it to an AI client.
Get practical integration notes and launch examples for MCP servers like llm-kosh.
uvx llm-kosh{
"CARTRIDGE_WORKSPACE": "YOUR_VALUE_HERE"
}Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"io-github-rastogivaibhav-llm-kosh": {
"command": "uvx",
"args": [
"llm-kosh"
],
"env": {
"CARTRIDGE_WORKSPACE": "YOUR_VALUE_HERE"
}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
llm-kosh is an MCP server for Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.. It supports STDIO transport.
Use the generated config in Install. This server runs with uvx llm-kosh; add any required environment variables before starting your client.
Choose the Claude Desktop tab in Install and copy the config for uvx llm-kosh. Add required environment variables before starting Claude Desktop.
Choose the Claude Code tab in Install and copy the config for uvx llm-kosh. Add required environment variables before starting Claude Code.
Choose the Codex tab in Install and copy the config for uvx llm-kosh. Add required environment variables before starting Codex.
Choose the Cursor or VS Code tab in Install and copy the config for uvx llm-kosh. Add required environment variables before starting Cursor or VS Code.
llm-kosh uses STDIO transport. Use the package or command config in Install.
llm-kosh inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
llm-kosh is marked with Auth required by registry metadata auth. You may need provider login, an API key, a bearer token, or a session header.
| Package | Registry | Version | Inputs |
|---|---|---|---|
llm-koshstdio | pypi | 2.1.0 | Env: CARTRIDGE_WORKSPACE required |