Plugins

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.

HarmonyOS device bridge: hdc screenshot/install/log/crash/UI automation loop with read_image, official-first versioned API knowledge (SDK .d.ts + offline bundled docs), and a DevEco CLI build/sign/lint lane.

Browser automation (Playwright) with a live view, an MCP server exposing DSH agents to any MCP client, and GitHub issue/PR/webhook review tools.

Auto-compaction that writes a handoff note first: as a session approaches a token threshold it asks the model to save a project checkpoint into the workspace, then optionally starts a fresh session seeded with a continue instruction and parks the old one. The note must be written within the current compaction cycle and its conclusions section must actually change, so a stale or merely touched file cannot slip through.

A persistent AI companion for DSH that explores Bilibili, interacts with permission controls, and grows through evidence-backed life memories, evolving interests, simulated emotions, social relationships, and autonomous to-dos.

One-shot mcp-unity integration for DeepSeek Harness: bundled MCP server with zero manual config lets the agent drive the Unity editor through 34 tools - scenes, game objects, transforms, materials, prefabs, menu items, play mode, tests and console logs - with auto-reconnect.

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

A self-contained second brain for DeepSeek Harness — auto-captures durable dialogue knowledge into a local Markdown vault (custom dedup, CJK search, git-friendly), with a graphical knowledge base and an interactive knowledge graph (legend filter, time-dimension coloring, box-select, merge, delete, PNG export/import).

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.

Anatomy panel for the Agent-Body organs: serves a live vitals dashboard at /anatomy inside the harness itself - organs, heartbeat, healing ledger, self-training counters and the real pulse stream - read straight from the runtime files rather than retyped. Host-only, no client bundle and no build step.

Zero-residence context engine: large tool payloads are evicted out of the live context into a queryable store and only deterministic pointers are left behind, so per-turn prompt tokens stop growing with the transcript. Any masked content is reconstructed verbatim from the session log on demand, by tool-call id or session seq.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

The memory organ of Agent-Body: after 2 minutes of silence it enters light sleep and after 5 minutes deep sleep, where deterministic rules distil real experience into memory cards (pitfalls, playbooks, hotspots, unresolved issues, facts). Incoming commands recall related cards by keyword and inject them into context; cards unused for long decay on a half-life and are archived rather than deleted. It also de-noises body-wide homeostasis warnings: repeats inside a window are counted instead of re-printed, and a warning that keeps recurring without ever healing converges into a known steady-state offset and goes quiet. Consolidation and recall make no model calls.

Plugin governance: new/updated plugins stage in a candidate area first, then hot-mount after startup — success promotes, failure auto-disables, repeated failures freeze, one-click safe mode, sidebar diagnostics panel (npm: `dsh-my-guardian`).

Task reliability: auto-retry on model timeouts/failures, auto-continue unfinished tasks, completion verification, thinking-repeat interruption, resume after sleep or restart, autopilot mode and a remote trigger endpoint (npm: `dsh-task-reliability`).

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

AI 原生智能爬虫与 JavaScript 逆向工程平台，基于 DSH、Patchright/CDP 与独立语义运行时，从浏览器证据恢复参数生成逻辑并交付可验证 Solver。

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

DSH input assistant for next-message prediction, draft autocomplete (text completion), and prompt polishing/rewrite. Session-local suggestions; Tab accepts into the draft without sending. Requires a configured model; calls may incur charges. Source-available; modifications require prior written permission.

Wraps the local GitHub CLI (gh) in agent tools for pull requests, issues, Actions runs, repository search and raw API calls, plus /gh status and /gh help slash commands and two web panels (a global repository cockpit and a per-session workspace panel).

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.