Plugins

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

Block-addressed document editing: an MCP server exposing geml_get / geml_set / geml_check and friends, so an agent reads or rewrites one addressed block of a Markdown or GEML document instead of the whole file. Ships the GEML authoring skill and a code-graph skill that builds and navigates a project call graph as GEML codemaps.

A cute whale-girl desktop pet for the DeepSeek Harness Web UI: pat-to-raise growth, live work-state poses, 494 dialogue lines, 30 achievements and a built-in settings panel — all local, zero telemetry.

Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.

Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网（安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析）。

Bridge the Pi and DeepSeek Harness ecosystems: a general Pi Host ABI that runs unmodified Pi extensions as native DSH plugins, plus per-package conversion and MCP config translation.

DeepTrace — deterministic agent reports from session logs (daily/weekly/monthly/yearly/custom): cost & token breakdown, 8 insight rules, collaboration review, live provider balance, PDF/PNG/HTML export; read-only, never rewrites history.

Feishu/Lark bridge for DeepSeek Harness: scan-to-connect PersonalAgent binding, streaming cards, git-worktree project workspaces, parallel per-scope tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian that still answers in Feishu after dsh crashes.

LAN/remote access for the Web UI: injects a crypto.randomUUID polyfill on plain-HTTP origins so the frontend survives LAN or Tailscale IP direct links.

Mounts 88 packaged research, social-intelligence, marketing and business Agent Skills into dsh through the filesystem Skill provider.

Create, edit, inspect, and deliver spreadsheets, documents, presentations, databases, and canvases in DeepSeek Harness, with live preview and worktree review.

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.

Recall any user message: rolls the conversation (official session fork) and workspace files (per-message shadow git snapshots) back to before it, with a diff-preview confirmation panel.

Claude Science-style research workbench: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), and 10 science skills for genomics/pathogens/bioinformatics.

A "focus chat" minimal view that shows only final outputs.

GitHub-style usage heatmap dashboard: per-workspace turn counts and token spend (with cache-hit rate), DeepSeek account balance, and workspace aliases.

Pop-out sidebar: lists artifacts and a file tree with multiple preview formats, pops out into a separate browser tab you can drag to another monitor, and coexists with other sidebar plugins simultaneously.

Finds potential UX issues in your project: automatically reviews React/TypeScript code, pinpoints each problem, and gives concrete suggestions.

OpenMAIC: classrooms, slides, interactive widgets, and Socratic teaching.

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.