Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:woshishadowhunter/dsh-seed-society
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.
唯识论八识架构的 Agent Society 插件：把 seed-society 的可审计双循环 运行时、dsh-mneme 记忆巩固调优、MCP 工具桥与六个种子技能，固化为一个 可直接安装的 DSH 插件包。
包含内容（安装后自动生效）
| 层 | 内容 | 载体 |
|---|---|---|
| 记忆巩固修复 | llm-deepseek.reasoningEffort: off（autoDream 根因修复，实测 57 次失败→成功） |
bundle patch |
| 记忆巩固调优 | mneme：autoDream on、32768 token、deepseek-chat、会话总结关 | bundle patch |
| MCP 工具桥 | mcp__society__*（run/enqueue/status/knowledge/genome/experience/approve…） |
mcp-client 实例 |
| 种子技能 | yogacara-society/alaya/manas/mano/panca/sila 六个 SKILL.md |
随包 + 镜像到 ~/.dsh/skills |
前置条件
- DSH（含
@deepseek-ai/dsh-llm-deepseek，基础包自带）； - Python 3.10+（MCP 桥与运行时）；
@modusensus/dsh-mneme（安装脚本自动装；注意超市注册表里的dsh-mneme名字是错的，真实包名是作用域的）。
安装（一条命令）
powershell -ExecutionPolicy Bypass -File integrations\dsh\install-plugin.ps1
脚本依次：pip 安装 seed-society → 装 mneme → 装本插件（pnpm add +
bundles 对账）→ 同步技能到 ~/.dsh/skills → dump-config 校验。装完重启
DSH（新 bundle 层需要重新组合）。
手动安装
python -m pip install -e <repo> # 1. python 运行时
dsh plugin --profile web add @modusensus/dsh-mneme # 2. mneme 前提
dsh plugin --profile web add github:woshishadowhunter/dsh-seed-society # 3. 本插件
# 4. 技能：复制 skills/ 下的六个目录到 ~/.dsh/skills/（或 ~/.agents/skills/）
仓库
- 主项目（运行时/文档/测试）：https://github.com/woshishadowhunter/seed-society
- 本插件：https://github.com/woshishadowhunter/dsh-seed-society
验证
dsh --profile web --dump-config | grep -E "mcp-society|reasoningEffort|dreamMaxTokens"
# 重启后：
# - 模型工具里出现 mcp__society__*
# - mneme 的 autoDream 继续巩固（dream_runs 出现 degraded/ok 行）
发布到插件超市（可选）
在 awesome-dsh-plugin 提交注册条目：
{
"name": "dsh-seed-society",
"owner": "woshishadowhunter",
"url": "https://github.com/woshishadowhunter/dsh-seed-society",
"category": "memory",
"description": { "en": "...", "zh": "..." }
}
注册表快照更新后，用户即可 dsh plugin --profile web add dsh-seed-society
一键安装（需先发布 npm 包，或在注册条目中用 github URL）。
边界
- 插件只做配置组合与桥接：不改验收标准、不给模型权限、不绕过审批；
- mcp-society 需 Python 环境；服务端不使用 shell、不持密钥；
- mneme 的 LLM 仲裁与其 CAS/快照哈希审计保持原样。
Links
More in this category
vectorize-io/hindsight#coding-agents★ 50109
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★ 40027
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.
agentscope-ai/ReMe#dsh★ 3610
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★ 2752
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★ 1205
Reads the session files thirty-three 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).
adoresever/graph-memory★ 649
Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.