dsh-soul-md
DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件:设置页输入人设卡名称和内容即可,文件由插件自动管理;可按工作区指定人设、聊天框可给会话单独切人设;AI 可自行演化人设与记忆(soul_read/soul_update/memory_*)。
394 results
DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件:设置页输入人设卡名称和内容即可,文件由插件自动管理;可按工作区指定人设、聊天框可给会话单独切人设;AI 可自行演化人设与记忆(soul_read/soul_update/memory_*)。
Unified agent memory for DeepSeek Harness — one shared Obsidian vault for every agent (dsh, Codex, Claude, Hermes). Ships the dependency-free Python core (search/promote/adjudicate/forget), a vault template, and a dsh plugin with memory_search / memory_show / memory_submit / memory_status tools. · 统一 Agent 记忆系统:多 Agent 共享一个 Obsidian vault,附零依赖 Python core 与 dsh 插件。
A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent can define, assert against, and query under schema constraints.
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity
DSH plugin: one settings panel for MCP servers, skills, scenes, memories, subagents, AGENTS.md presets and archived sessions — scene memory injects into the system prompt, scene lock freezes all five domains, deleted workspaces re-register with one click. Settings UI + HTTP API + 14 model tools (mcp_manager_*, skill_manager_*, prompt_manager_*, memory_manager_*, subagent_*). Install with one command: dsh plugin --profile web add dsh-plugin-tool-management@latest
DeepSeek Harness 的 TencentDB Agent Memory 移植:L0 对话捕获 → L1 结构化记忆提取 → L2 场景/L3 画像,自动召回注入 + 记忆/对话搜索工具;复用现有 ~/.memory-tencentdb/memory-tdai 数据;附 Web UI 设置栏。
One memory layer for every AI tool and agent, packaged for DeepSeek Harness with startup context, prompt-time recall, Mem MCP tools, and DSH thread capture.
File-based memory plugin for DeepSeek Harness (DSH) — cross-session memory in transparent markdown files, with a memory star-map view
Context Assembler DSH V0.99 — Context Assembler plugin for DeepSeek Harness (dsh): context compaction, cache-friendly topic-block management, water-pressure topic splitting, tool trace/rewrite, handoff planning and reality recall injection.
Gives the DeepSeek Harness agent a configurable humanized whale-girl maid persona (address, self-name, speaking mode), an immersive no-plugin-meta rule, and a lightweight layered memory with query-triggered recall.
记忆核心(Memory Eternal):自研的 DeepSeek Harness 记忆插件,不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault(自研去重、自研 CJK 检索、可 git 管理),设置页提供图形化知识库(统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗),Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。
Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScript sources, built with tsc + esbuild.
记忆核心(Memory Eternal):自研的 DeepSeek Harness 记忆插件,不移植任何既有记忆框架——对话结束后自动沉淀知识卡到本地 Markdown Vault(自研去重、自研 CJK 检索、可 git 管理),设置页提供图形化知识库(统计 / 搜索 / 知识图谱 + 侧边栏一键弹窗),Agent 通过 memory_recall 工具按需召回历史上下文。零人工干预。
Obsidian side-panel math memory agent for DeepSeek Harness: layered long-term memory, idea memo with proactive review reminders, unified note_recall retrieval plus dedicated note search/create/backlink tools. Ships as both a dsh plugin and an Obsidian community plugin.
DSH web plugin: per-host personalization — global custom instructions, local long-term memory (collect / retain / integrate / manage), and reply tone presets.
Cross-session memory vault for DeepSeek Harness: remember / recall / forget tools, per-turn prompt injection, and a browser management page.
DSWM — Simple Wiki Memory for DeepSeek Harness: a self-maintaining persistent memory system (index + reference/pending/archive + git backup + memory skills).
Curated, verified MCP server bundle for DeepSeek Harness (dsh): one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, with a connectivity verifier and CI checks.
定时自动化 · 用量趋势 · 技能与 MCP Server 管理 · 自动沉淀的长期记忆——一套插件装齐 DSH 四个工作台。纯插件注入,不动官方源码,一句话安装。
Evidence-driven learning memory and automation for Git-native AI agents
Task-isolated long-term memory for DeepSeek Harness: remember / recall / search stay inside one task boundary, with optional prompt injection.
Claude Code-style @path imports for DSH: expands @imports in AGENTS.md/CLAUDE.md and injects the referenced files into model context at session start
Bridge OpenCode's skills and configuration into DeepSeek Harness
Official hybrid DSH plugin: Cheat Engine dynamic debugging toolkit with host ce_* tools and a client floating status panel.