LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:ljsysfurryACE/dsh-memory-director
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
dsh-memory-director
MemoryDirector 插件 —— 给 DeepSeek Harness 加"长期记忆"能力。
官方 Harness 的 compaction 只做摘要压缩，没有任何"跨会话记住重要事实"的概念。 这个插件补上 AgentFrame 的 MemoryDirector：
- 每轮对话后：LLM 分析本轮，决定记住什么 / 忘记什么
- 每次请求前：检索相关记忆，注入模型上下文
- 持久化：记忆存 JSON 文件（
~/.dsh/memory.json）
为什么是差异化
| 能力 | 官方 Harness | dsh-memory-director |
|---|---|---|
| 上下文压缩 | ✓ compaction | ✓ (可配合) |
| 记住重要事实 | × 没有 | ✓ LLM 决策 |
| 跨会话记忆 | × | ✓ 持久化 |
| 记忆检索注入 | × | ✓ pre-step 注入 |
| 遗忘管理 | × | ✓ 重要度衰减 |
接入
# profile 的 cordis.patch.yml
- id: memory-director
name: '@agentframe/dsh-memory-director'
config:
provider: deepseek-official
model: deepseek-v4-flash
maxTokens: 256
dedupThreshold: 0.8
forgetThreshold: 0.1
storePath: ~/.dsh/memory.json
auto: true
机制
agent/turn-stopping (每轮结束)
→ 提取本轮文本 → LLM 决策 {remember, forget, importance}
→ remember → 存入记忆库 (去重)
→ forget → 删除过时记忆
agent/pre-step (每次请求前)
→ 取最后用户消息 → 检索相关记忆
→ 注入 system 消息 (memory-director block)
→ 模型可基于记忆回答
配置
| 字段 | 默认 | 说明 |
|---|---|---|
provider |
deepseek-official | 决策用 provider |
model |
deepseek-v4-flash | 决策用模型 (便宜快速) |
maxTokens |
256 | 决策输出上限 |
dedupThreshold |
0.8 | 记忆去重阈值 |
forgetThreshold |
0.1 | 遗忘阈值 (重要度衰减) |
storePath |
~/.dsh/memory.json | 持久化路径 |
auto |
true | 自动挂钩 agent 循环 |
License
GPL-3.0 © Cloud LTE Studio / AgentFrame
Links
More in this category
vectorize-io/hindsight#coding-agents★ 60728
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 42125
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
MemTensor/MemOS#memos-local-plugin★ 12376
Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.
agentscope-ai/ReMe#dsh★ 3796
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2866
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1529
Reads the session files forty-two other coding agents on this machine already wrote (Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more), including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.