Plugins

Local knowledge base manager for DSH agents: multi-format import, CJK-aware chunking, sqlite-vec vector + BM25 hybrid search with bge-reranker-base rerank, snapshots, kbpack export/import and cross-KB search — 22 agent tools plus a Web panel.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory). v0.8.1 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.8.1 or newer.

Search AIGC Radar's curated GitHub AI project library (500-star admission, bilingual zh/en tags, star-growth snapshots) over its MCP endpoint with native result cards; an agent/pre-step listener proactively suggests a reuse check before the agent writes code.

Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.

Drive Jiey Browser from DeepSeek Harness over MCP: navigate, snapshot, act, read, screenshot, and manage tabs in a real Chromium profile.

Open and edit Visio (.vsdx) drawings in a DSH panel: live SVG preview, shape and connector editing, layout checks, and a visio tool so the agent can read and modify the drawing. The core engine is Python standard library and needs no Visio or Office; requires Python 3.9+ on PATH, and Pillow for PNG export, snapshots and stencil previews.

A DSH-native plugin update center: check and update installed plugins from the sidebar with snapshots, rollback, queued updates and uninstall-leftover cleanup.

Sidebar leaderboard for DeepSeek Harness (DSH): LMArena blind-test ratings, Artificial Analysis intelligence index, LiveBench 2.0 capability, OpenRouter weekly/monthly usage and market share, price, speed and context — plus a local token-usage dashboard built from your own session logs (tokens, estimated cost, per-model ranking), model detail drawers and CSV export. Daily snapshot, instant open, no API key; locally configured models are highlighted.

Layered system-prompt profiles — global, per-workspace and per-session entries injected in order — where individual builtin sections and runtime contexts can be disabled or overridden, with a line-level diff of what an override changed; each entry carries a subagent scope that targets the main agent only, subagents only, or both; assembly snapshots record what each turn actually received, subagents included. Managed from a Web panel and a `prompt_manager` tool.

Reads one Genshin Impact account (characters, talents, weapons, artifacts, wish history) into a single snapshot, then exposes it as six agent tools and a six-tab panel. Artifact substats come from the public in-game character showcase; scoring ships both CV and per-character weight models with six grade tiers; wish analysis covers pity, luck tiers and per-pool progress. Needs a Miyoushe QR login to read characters, weapons and wish history; showcase data is public by UID.

Black-box GUI testing for DeepSeek Harness: an AI tester drives a real Windows virtual machine using only screenshots and mouse/keyboard, so its verdicts rest on pixels instead of logs or source code. Ships the dsh-vm-tester plugin with twelve vm_* tools (status, UI tree, screenshot, click, type, type-secret, key, basic key, wait, snapshot, upload, download), a reverse-tunnel guest agent for Windows, and run verification scripts. Needs Windows, VirtualBox 7 and a Windows guest VM with the bundled agent before any vm tool works.

A wx_archive tool that turns a WeChat Official Account article link into a permanent Markdown snapshot via the 2100laike archive service: images are re-hosted so they never break, snapshots survive article deletion, resubmits dedup-hit and return the latest version without spending quota, a content_kind field tells text articles from sticker (image-post) messages, and refresh forces a refetch with a PAT. Needs the third-party 2100laike service; anonymous use is limited to 8 archives per day per plugin instance and a registered PAT raises that to 100 per day.

Backup, restore and machine-migration for DSH: packs skills (which live outside ~/.dsh, in ~/.agents/skills), plugin manifests, core config, memories, todos and optionally sessions into a tar.gz with a sha256 sidecar, then imports it on another machine as a three-way merge against a baseline, listing per-file differences instead of overwriting changes made there. Credentials never enter an archive (filename deny-list of 27 names plus 7 private-key suffixes plus a content gate, enforced again on the import side), every import writes a pre-restore snapshot first, and an archive can be uploaded to any WebDAV server and pulled back on the new machine. Also includes scheduled backups, a read-only viewer for individual files, and an in-panel cloud card; no npm runtime dependencies (packing uses the system tar).

Markdown-as-database project knowledge base for DSH agents: ten kb_* tools (including kb_register for registering existing notes), stable TIDs, `[[node]]` links that never copy text, `[[tscl]]` definitions expanded in place, bounded reads, structural lint covering tscl, workspace-first library discovery, inline git snapshots, a node-graph panel, and a bundled prompt section plus skill that make the agent reach for kb_* instead of hand-written docs/.

DeepSeek Harness plugin: restart without losing work. It waits until every conversation is idle, restarts the host, and picks the interrupted work back up instead of dying with it; where a supervisor already manages the host it asks that supervisor, and it never starts a second host next to a running one. It also fixes a common one: stale login cookies pile up on every launch until the request header overflows and the host will not start; the plugin clears them before each restart. Every restart is preceded by a snapshot of the configuration and the installed plugins - 2 are kept by default, up to 10 are allowed, and old or incomplete ones are pruned. That snapshot is never applied automatically: the plugin does not watch the host and does not restore anything on its own; it is only there for you to look at, or to roll back by hand. When the work is done it counts down and powers the machine off, so nobody has to stay up at night. It works on the Windows desktop client, and on a hosted dsh web instance - verified on WSL with systemd; Windows-hosted web, WSL without systemd, and native Linux are untested.

Provider-reported quota snapshots for GLM Coding Plan and GitHub Copilot in DSH: a draggable floating capsule with detail panels for quota windows, reset times, per-model usage and Copilot credits, plus an optional sidebar card hidden by default; credentials are resolved by the DSH host and no quota history is stored.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.

Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon

Cron task scheduler for DSH: on schedule, automatically creates a new session and injects your prompt as its first message, with task history and manual run/stop controls. Also runs KNJ workflows: pick files directly (stored as persistent snapshots, re-handed to the workflow on every fire) or reference them by path. Its panel is registered in the settings page (settings.section), so no separate menu plugin is required.

Current-session message outline rail for the DSH web UI — your messages show as slim bars on the left edge; hover to expand the full outline (line number + text), click to jump instantly to that message. Pure frontend, zero external service dependencies, sessions-snapshot driven with zero polling.

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.