dsh-engram
Cross-session long-term memory under the "memory palace" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof ranking boost, automatic capture from the session log (including the final turn), provenance audit chains, consolidation distillation and decay forgetting, and a settings-page Memory Library panel with corridor topology, tour butler, and refurb list.
跨会话长期记忆插件，以「记忆宫殿」隐喻重构 agent 长期记忆：双层 SQLite 分库（用户级 + 按 git origin 隔离的项目级）、FTS5 + 本地向量 RRF 融合与新鲜度/命中排序 boost、从会话日志自动摄取（含末轮）、来源审计链、巩固蒸馏与衰减遗忘，以及设置页「记忆库」面板（走廊拓扑、导览管家、翻新清单）。
How to install
dsh plugin add @kenz1117/dsh-engram About
dsh-engram 中文 | English --- 快速开始 sh dsh plugin --profile web add @kenz1117/dsh-engram 安装后无需配置即可使用（默认分库与模型缓存在 ~/.dsh/engram，画像注入开启，自动摄取关闭）。 特性 **跨会话记忆**：会话开始注入用户画像摘要（条数 + token 预算双重上限，可配），Agent 天然"记得"你是谁、在做什么；工具检索跨会话召回历史事实。 **双层分库**：user.db 全局共享；project-<hash>.db 按 git origin 标识隔离（无 git 时回退工作目录编码，旧库自动迁移）——个人偏好跟人走，项目约定跟仓库走。 **混合检索**：FTS5（unicode61 + 中文 2-gram 预切词）与本地向量（Xenova/bge-small-zh-v1.5，512 维，q8）RRF 融合 + 关系边一跳扩展 + 新鲜度/命中次数乘性排序 boost；嵌入模型离线运行，下载失败自动降级纯关键词并显式标记。 **知识飞轮**：摄取/保存 → 矛盾候选（写入时高相似近邻建 contradicts 边并报告，模型/用户裁决）→ 命中强化（confidence +0.05）→ 蒸馏（同主题簇合并为高层规律、supersedes 取代链、置信度继承）→ 衰减（低重要性且长…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 7
- mo. downloads
- 4.4K
- Last push
- 2026-09-22
- Created
- 2026-09-01
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent, awesome-dsh-plugin, deepseek-harness, dsh, dsh-plugin, embeddings, memory, sqlite
Related plugins
dsh-memory
FuRongJun-1999/dsh-memory
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
dsh-pua
MichengAI/dsh-pua
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
dsh-heartbeat
Kanadego/dsh-heartbeat
Heartbeat loop for DeepSeek Harness: every 20 minutes (by default) the agent wakes on its own to keep a local profile of your interests and preferences, search the web for things you care about, and keep what it finds. When it has something worth sharing, it sends a short package of notes to the sessions you link it to. A set of rules in code - quiet hours, busy windows, a daily limit, a cooldown - decides whether it may speak at all, and the agent in that session decides whether to actually say anything. Windows only.
dsh-answer-reviewer
bycall/dsh-answer-reviewer
Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.