Architecture, safety charter, quickstart, and philosophy for Starshard — a substrate for multi-agent personal AI where user-owned memory is the primary layer and agents are peripherals.
-
Updated
Oct 16, 2026
Architecture, safety charter, quickstart, and philosophy for Starshard — a substrate for multi-agent personal AI where user-owned memory is the primary layer and agents are peripherals.
The only AI agent memory with a tamper-evident audit chain. Local SQLite, no cloud, MCP server, bi-temporal supersession, conflict gate.
Phase 0 reference server for the Starshard memory hub: FastAPI + SQLite + MCP bridge, giving any Claude Code / Codex / MCP agent persistent memory across sessions and machines.
To associate your repository with the memory-hub topic, visit your repo's landing page and select "manage topics."