Local memory for Codex. Reuse work across chats without LLM calls to organize it.
-
Updated
Sep 13, 2026 - Lean
Local memory for Codex. Reuse work across chats without LLM calls to organize it.
Local-first AI project memory and control runtime for evidence, privacy, model routing, human approvals and cross-harness handoffs.
Autonomous 7/24 Ed25519 agent & living isometric pixel observatory for Technocore (twg1 protocol). Verifiable useful work, atomic CAS /kv/ state, and real-time cyber-metropolis.
Persistent multi-agent work graph and document-state machine for contracts, specs, slices, evidence, verification, handoffs, and cost-aware AI execution.
To associate your repository with the work-graph topic, visit your repo's landing page and select "manage topics."