memxt

Local-first long-term memory for AI coding agents

session wake-up
~10 ms
warm vector search
<1 ms
no Python or Docker
1 binary

The thesis

Your Agent Can Forget the Chat. It Should Not Forget the Work.

The fastest benchmarked open-source AI memory system — a single static binary that gives coding agents persistent, on-device memory across sessions. No cloud, no Python, nothing leaves your machine.

Built for: Developers who want coding agents to remember architecture, decisions, and working context across sessions without sending that memory to a cloud service.

What it changes

Complex Machinery, Direct Experience

Wake Up with Context

MCP tools and session hooks give an agent relevant project memory at the start of a session instead of another blank slate.

Keep Recall Out of the Way

A Zig binary, local embedding model, llama.cpp, and sqlite-vec keep semantic search fast enough to become invisible infrastructure.

Keep Decisions On-Device

Embeddings, storage, and search stay on the machine. There is no hosted vector database and no API key at query time.