DiligenceLai/dsh-memory-ga

DiligenceLai★ 0JavaScript最后同步: 2026-08-22

在 GitHub 打开

Gated GA-style layered memory for DeepSeek Harness: hard-injected L1 index + RULES, session working checkpoint, settlement ritual to Skills/L1/L2 - no silent auto-retain.

README 摘要

dsh-memory-ga Gated, file-based long-term memory for DeepSeek Harness — inspired by GenericAgent’s discipline: No Execution, No Memory . Your agent already has Skills. What it usually lacks is a small, trustworthy index of facts + rules , a session notepad , and a settlement ritual that turns hard-won lessons into Skills / facts — without silently poisoning memory from every chat. Language: English · 中文 Why this exists Coding agents forget. Vector “auto-memory” products remember too much — drafts, wrong turns, guesses. dsh-memory-ga takes the other path: Principle What you get Verified only Long-term writes only after tools (or the user) confirmed reality Hard-injected L1 A ≤ 30-line index + RULES every turn — not a pointer you might never open Working notepad Session key info re-injected while non-empty Gated settlement start long term update opens a protocol; it does not auto-edit your files Skills stay Skills Reusable procedures → DSH Skills. Memory is not a second SOP warehouse Local & auditable Plain UTF-8 under $DSH HOME/memory — diff, backup, hand-edit No embeddings required. No cloud bank. No silent retain. Architecture (deliberately small) There is no L3 notes library and …

在 GitHub 查看完整 README →
工具/开发agent-memorycordisdeepseek-harnessdsh-pluginmemory-managementagent

分类