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.
Local-first long-term memory for AI coding agents
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.
MCP tools and session hooks give an agent relevant project memory at the start of a session instead of another blank slate.
A Zig binary, local embedding model, llama.cpp, and sqlite-vec keep semantic search fast enough to become invisible infrastructure.
Embeddings, storage, and search stay on the machine. There is no hosted vector database and no API key at query time.