Plugins

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

为 DeepSeek Harness 带来「跨会话长期记忆 + 后台自我进化」能力的纯插件实现：五轨记忆 · git 分支感知 · 回合内自我审查 · 技能自我进化与技能管理器 · 四轨待办 · COI 调度 · 会话广播 · 会话搜索 · 提示词管理器 · 临时信息便签——零核心修改、零运行时依赖，随装随用、卸载即净。

Deep Mnemon integration: local three-tier memory (Runtime Memory, retrievable Documents, supervised Memory Spaces).

Cross-session memory: SQLite with a human-editable Markdown mirror, background consolidation (dedup, merge, conflict resolution), and six memory tools.

DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.

Bridge Claude Code's memory, skills, and configuration into DeepSeek Harness — zero migration, full compatibility

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Carry durable task state across DeepSeek Harness, WorkBuddy, Claude Code and Codex with machine-readable checkpoints and optimistic locking.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

DSH 自动记忆插件:三层记忆(用户级/项目笔记/每日日志)自动注入与检索、每日反思、可视化面板与设置页,支持继承其他 AI 工具的历史记忆。An auto-memory plugin for the DeepSeek Harness Web GUI: three-layer memory (user-level / project notes / daily logs) with automatic injection and retrieval, daily reflections, a visual panel and settings page, and inheritance of memories from other AI tools.

Per-host personalization for DSH: custom instructions, local long-term memory, and reply-tone presets.

Curated MCP server bundle: one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, plus a connectivity verifier tool and CI checks.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Task planning with experience muscle-memory: condition-reflex recall of past solutions, LLM capability matching, and auto-persisted lessons.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection; every write passes the approval gate and stays reconstructable from the session log.

Structured long-term memory system for DeepSeek Harness -- unit-based brief/full pairs with auto-injection

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。

User preference memory for DeepSeek Harness: persisted user profile with memory_get/memory_update tools and system-prompt injection

Bridge OpenAI Codex's memory, skills, and configuration into DeepSeek Harness

Read-only Windows device information tools: one agent tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers) via WMI/CIM and Node os collectors.

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Project-scoped cross-session memory: PROJECT.md snapshot injected into the first user message, a memory_remember tool, and auto-reflection after ReAct tasks; each project keeps its own memory file.

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.