Plugins

Mebular · shared memory and task collaboration for agents. Through a DSH-native plugin it offers cross-device, cross-agent memory sharing and task graphs. The plugin attaches to an existing Mebular app or CLI runtime, and its panel installs the shared runtime on demand when none exists; it never starts or downloads Mebular silently.

Causal memory for dsh: a zero-dependency MCP stdio bridge that mounts the 17 tools of the causal-memory server under clean names (no mcp__ prefix) — decision → outcome edges with typed relations (caused / enabled / prevented) in a local SQLite store that survives compaction — plus a pinned system-prompt section. Requires the causal-memory server binary on PATH (pip install causal-memory, or a prebuilt release).

Scheduled coding runs in fresh agent sessions with auditable history.

Paste a link; the agent reads it. Xiaohongshu, Douyin, Bilibili, WeChat, articles, PDFs and audio become citable Markdown for a wiki or knowledge base. On 60 turns with vs without: finishes reading 22% -> 92% (+70 points), times out 68% -> 0%, answer quotes a real source fact 23% -> 82% (the A/B is exploratory: different time caps, no human correctness review). On 123 live links 80% came back usable (93% of the pages that answered); an unreachable link reports in 26 s. Codex, Claude Code, DSH.

View and manage an agent’s tools and skills in a visual menu. Set each capability to Resident, On-demand, or Disabled; agents can find and use on-demand capabilities while reducing context usage.

Connect any ACP-capable agent to DSH and use DSH as a single entry point for all conversations and tasks. Models, thinking levels and permission modes come from the agent itself; tool calls appear in the main chat, diffs are collected on a dedicated NTR page, and approval requests appear in the composer. Requires an ACP-capable agent CLI installed locally.

Knowledge base for DeepSeek Harness: assembles ContextWindow evidence at query time within heading boundaries and token budgets, with follow-up reading around each search anchor; combines BM25/vector search via weighted RRF, MMR and optional local/remote reranking; provides automatic evidence injection, a browser panel for local embedding/rerank/OCR model downloads and health checks, keyword search without model downloads, and in-place rescans of imported directories.

A plugin management panel: one-click enable/disable for installed plugins plus a GitHub dsh-plugin marketplace with details and one-click installs.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Runs Midscene on the models already configured in DeepSeek Harness instead of separate third-party API keys: hosts an OpenAI-compatible bridge on 127.0.0.1 (default port 8787, automatically skipping occupied ports) that proxies chat completions, streaming and non-streaming, to the DSH host model layer, so DeepSeek official routing, CodeBuddy, Codex and custom OpenAI/Anthropic endpoints all become available to Midscene agents while credentials stay inside the provider plugins and the bridge never touches them. A `/v1/midscene-env` endpoint generates the four MIDSCENE_MODEL_* environment lines with the model family inferred, and seven built-in skills — browser, desktop, Android, iOS and HarmonyOS automation plus a Vitest E2E skill and a Midscene knowledge reference — appear in the session skill catalog without `npx skills add`. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-midscene`.

Asset governance console for self-hosted AI infrastructure. Registers MCP servers, skills, agents, AI apps, model channels, SaaS connectors and NAS storage in one ledger with a lifecycle state machine, per-tool RBAC permission points, department x agent x skill cost attribution, dependency topology and an append-only audit trail. Self-hosted, MIT, no hosted tier and no cloud contract.

Word alternatives and underscore-gated fill-ins in the composer. End a line with _ and it is filled; misspellings are flagged as you type. Routes through the model dsh is already configured with, so it needs no API key.

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

Skill-driven harness/loop engineering workflow agent plugin.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Third-party adapter that registers the upstream REA (Reverse Engineer Anything) MCP server into DeepSeek Harness as mcp__rea__* tools. 2.x provisions its own runtime (Node, the REA CLI, a JDK, Ghidra) under <DSH_HOME>/plugins/rea-bundle and launches REA through a shim, so a machine with nothing pre-installed works after one setup run; 1.x (branch v1, npm 1.0.6) is configuration-only and expects REA and Ghidra to be installed already. Analysis is upstream's: native binaries (Hopper/Ghidra/IDA), JavaScript/Electron apps, .NET assemblies, websites, Android APKs and adb devices, firmware, and process captures.

Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.

Keeps a local TinyTitan model server reachable from the harness: refreshes the llm-pi-ai route from the installed models and mounts a compaction backend that does not think.

The DSH plugin-development knowledge base as an on-demand agent skill: official constraints, task workflows, API reference and community gotchas, installed with the bundle so the agent can look things up while building a plugin.

Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin project), hybrid FTS5 + local-vector retrieval fused with RRF, an evidence gate that forces an explicit sufficiency judgement, provenance audit chains, SM-2 spaced-repetition review, consolidation distillation and decay forgetting, and a nine-view "Memory Palace" sidebar panel. 22 narrow-parameter tools, no external service, no API key, no Docker.

WSL workspace support for DeepSeek Harness——无缝的 WSL 工作区使用体验，无需在 WSL 之中再安装一个dsh，安装该插件后在 GUI 里直接添加 WSL 工作区即可。WSL workspace support for DeepSeek Harness — Enjoy a seamless WSL workspace experience without needing to install dsh inside WSL. Once this plugin is installed, you can directly add a WSL workspace right from the GUI.

Host page for kit plugin configuration in the DSH Web GUI: registers a "Plugin configuration" section in Settings — peer to the built-in General section — through the official settings.section slot and declares a settings.kit.item child slot, which dsh-plugin-kit plugins render their own config cards into. Installing it alone shows an empty page; cards appear as slot-registering kit plugins are installed.

QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.

Cleans the harness prompt-authority layer into a reviewable patch set, writes prompt-inject.md and lets each model use a different default prompt, reports which patches took effect and whether the running host loads app.asar or an unpacked tree, and swaps a sealed install to the patched tree once the desktop process is idle. Includes a status page and the dsh-purge CLI.