A cognitive memory architecture for agents: ACT-R activation, association, consolidation, and forgetting. sqlite, zero dependencies.
-
Updated
Aug 4, 2026 - Python
A cognitive memory architecture for agents: ACT-R activation, association, consolidation, and forgetting. sqlite, zero dependencies.
A privacy-first, receipt-driven memory layer for multi-agent workbenches on Windows. | 面向 Windows 多 AI 工作台的隐私优先、可审阅记忆治理层。
Event-Driven Cognitive Execution Engine for AI Agents — 612 lines of pure Python, zero dependencies. BM25 retrieval + 5-type classifier + negation detection. Deployed in production for CiteFlow's 3 AI Agents.
Memory engineering for AI agents as an installable skill — what to write, where it goes, when to delete. Bootstrap interview + memory audit. Working/episodic/semantic/procedural mapped to real files.
Add a description, image, and links to the memory-engineering topic page so that developers can more easily learn about it.
To associate your repository with the memory-engineering topic, visit your repo's landing page and select "manage topics."