tinqiao-oss20412Updated today
File-based curated memory: a line/byte-capped `MEMORY.md` index plus one markdown file per fact, versioned with git and readable without a tool. The cap is enforced through `ctx.tools.guard()` rather than asked for in a prompt, and the protocol is registered as a runtime skill; the same store is also read by Claude Code, Codex, Kiro, and OpenClaw.
Practical score
88 / 100
Setup
Ready to use
License
MIT
Language
JavaScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/tinqiao-oss/engramory.gitPlease install the DeepSeek Harness plugin "dsh-engramory" for me. - GitHub repository: tinqiao-oss/engramory (https://github.com/tinqiao-oss/engramory) - Type: a Cordis plugin (installed into a DSH profile) - It should work out of the box with no extra config…
A cleaned excerpt from the project's own documentation.
简体中文 English Engramory Agent 通用长期记忆层。 AI 记住的东西存成一个个普通 markdown 文件，一个只放指针的索引 MEMORY.md 列出全部笔记，每次会话开头读进来，细节要用时再打开。不需要数据库、向量或服务器，文件你能直接看、能改。Claude Code、Codex、DeepSeek Harness（dsh）、OpenClaw、Kiro 等都能用；一个工具负责写，别的工具可以只读同一个库。 dsh 有专用插件 dsh-engramory ：装上就能用，自动带上索引，把索引写超上限的写入大多在落盘前就被拦下，侧栏还多一个记忆页。Claude Code 用 hook 拦超限写入；其他工具靠规则加校验脚本。 名字来自 engram （记忆痕迹）+ memory 。本项目是 tinqiao-oss/engramory （dsh 插件的 npm 包叫 dsh-engramory ），与其他所有者名下的同名仓库无关。 🤖 你是被要求安装或检查它的 AI agent？ 先读 AGENT-SETUP.md。 状态:1.5.2。…
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.
PerryLink
Bounded, layered, approval-gated, auditable cross-session memory: typed ctx.memory seam, zero-dependency SQLite provider, memory tool and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a conformance suite.
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`).