kenz11176710Updated yesterday
Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, provenance audit, SM-2 review. Zero external services, zero API keys.
Practical score
80 / 100
Setup
Needs setup
License
MIT
Language
TypeScript
Copy the command, or hand the whole task to your harness agent.
dsh plugin --profile web add @kenz1117/dsh-engramPlease install the DeepSeek Harness plugin "dsh-engram" for me. - GitHub repository: kenz1117/dsh-engram (https://github.com/kenz1117/dsh-engram) - Type: a Cordis plugin (installed into a DSH profile) - This plugin may need extra configuration (API key, token)…
A cleaned excerpt from the project's own documentation.
dsh-engram · 记忆宫殿 Local-first long-term memory for your coding agent. 纯本地 SQLite 的跨会话长期记忆： 零外部服务 · 零 API Key · 零 Docker ，一条命令装完即用。 23 个窄参数工具 · 混合检索（FTS5 + 本地向量 RRF）· 证据门 · 全链路审计 · SM-2 间隔重复复习 · 面板中英俄文。
Open on GitHubSimilar tools from the same corner of the ecosystem.
EternalNight996
Your AI forgets every session. Give it a memory you can audit: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes and MengBot (any MCP client), with an immutable audit log and a token ledger. Agents propose, humans approve. MIT, self-hosted, no cloud.
diqierjia
Local-first cross-session memory: L0-L5 layered short-term memory, event cards plus a knowledge graph, and evidence-gated retrieval with source tracing (npm: `stratagate-dsh`).
KKL08
沉淀、检索与治理一体的记忆插件，为你的 DeepSeek Harness 赋予可塑性记忆: Memory plugin with built-in curation and governance for DeepSeek Harness