Turn AI editor chat history into typed Markdown + AGENTS.md rules — local-first, git-trackable, zero .remember() calls.
ai-memory — Chat History → AGENTS.md + Cursor Rules + MCP is an MCP project maintained in the hyxnj666-creator/ai-memory repository. The maintainer describes its purpose as “Turn AI editor chat history into typed Markdown + AGENTS.md rules — local-first, git-trackable, zero .remember() calls”. Read the project documentation for the complete scope.
The documented npm package is ai-memory-cli. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"ai-memory": {
"command": "npx",
"args": [
"ai-memory-cli",
"serve"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
TypeScript inferred types, completions and type errors for AI coding agents
<strong>A multimodal local memory MCP for AI agents powered by Gemini Embedding 2.</strong>
A Model Context Protocol (MCP) server built in TypeScript that integrates with GitHub's API, enabling AI assistants to manage repositories, issues
</td> <td style="padding-left: 20px; vertical-align: top;"> <strong>Valentina Factcheck 💅</strong> <code>she/her</code>