All Plugins

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

ACP profile plugin and standalone stdio server for using the full DSH agent from Zed and other ACP clients while sharing DSH credentials and sessions.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

A theme appearance plugin that lets you fully customize the Web UI with custom theme colors, background wallpapers, and fine-grained transparency and blur controls for each section of the homepage, plus import/export support for easy theme sharing.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

Role-based LLM retry & fallback strategies.

Frame-level scan diagnostics for session files (torn/corrupt/empty detection).

Reuses the Codex CLI ChatGPT login as an `openai-codex` LLM route and adds GPT Auth controls to DSH Web settings.

Keyboard-first command palette for the DSH Web UI.

Claude-style drag-and-drop/paperclip file upload with content sniffing, document-to-Markdown via Microsoft MarkItDown (built-in JS fallback), text inlining, and a read_document tool for agents.

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.

Select part of a conversation and ask about it in a right-side side chat; bring AI replies back to the main chat directly or as a summary.

Bridge plugin for the [Better DeepSeek](https://github.com/EdgeTypE/better-deepseek) Chrome extension: exposes HTTP handshake and session-filtered SSE event streams over the web server, enabling browser-extension UI integrations with DeepSeek Harness.

OAuth 2.1 MCP client for Streamable HTTP servers: add a connection in Settings, sign in through the browser (PKCE with dynamic client registration), and have its tools registered in DSH, with tokens kept in the credential service and the connection written to the profile.

Project-scoped cross-session memory: six-layer SQLite store (soul/user/project/fact/lesson/topic) on node:sqlite, cache-friendly first-message injection, memory_remember/search/find_similar/read/update tools, and per-window nightly consolidation ("dream").

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.

Render Mermaid code fences in DSH Web chat messages as lazy-loaded SVG diagrams with strict sanitization and light/dark theme follow.

Appearance customization for the DeepSeek Harness WebUI: theme palette, wallpaper and video backgrounds, translucency and glassmorphism.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.