dsh-mnemon
omdsh-dev
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
GITHUB TOPIC
12projects include this topic
The "llm-memory" topic on GitHub groups 12 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-mnemon with 1k GitHub stars. dsh-mnemon — Composable, view-based context for DeepSeek Harness. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
omdsh-dev
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
tinqiao-oss
Agent 通用长期记忆层:Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档,文档以链接形式列在限长索引中,索引随会话自动注入。DeepSeek Harness(dsh)有专用插件 dsh-engramory。
ciskonc
Claude Code-style @path imports for DeepSeek Harness: expands @imports in AGENTS.md/CLAUDE.md and injects referenced files into context at session start
yu381792
五种载体,一座本地对话档案馆:原文归档、分层后台摘要、原文查证与跨工具接续。默认原生压缩,Claude Code 与 dsh harness 可选接管。Local archive, layered summaries and exact-source recall across five harnesses; native compaction by default.
xiangrui979
ForeSight: a temporal-aspect long-term memory plugin for DeepSeek Harness (dsh)
1luoyun
基于dsh环境制作,给 AI agent 用的类脑长期记忆:单文件 SQLite、事件是唯一真相、会遗忘(衰减/休眠/提炼)、题集评测。核心零依赖
3likofj
该插件是 DSH 上的可编程记忆编排层 + 自我进化引擎
gangwolf2312-creator
Memory Tree bridge plugin for DeepSeek Harness — auto memory extraction/injection, event graph, wiki graph, timeline, audit. · Memory Tree bridge plugin
plur-ai
PLUR memory for DeepSeek Harness — engrams injected into the system prompt, no tool call required. Local-first, Apache-2.0.
BTYG123
Tiered "sleep" compaction backend for DeepSeek Harness: the newest round owns T/3 of the context window, older tiers halve (T/6, T/12, …), and one model-written ladder replaces the shadowed history. MIT.
masquerator-coder
Layered long-term memory for coding agents: decaying episodic recall (L2), a provenance-tracking semantic graph (L3), and budgeted procedural skills (L4) in one embedded SQLite file. Deterministic retrieval, no model calls, no server. Ships a DeepSeek Harness plugin.
navid-kianfar
Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and session context in a queryable DuckDB file, with the rule set injected into every model request — plus a full management UI in the Web Client.