Plugins

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Provides the bili_summary tool: Bilibili video metadata, subtitle timeline, and sharp-based frame capture with built-in error handling and graceful degradation.

Floating workspace file-tree browser for the Web GUI with line-numbered syntax highlighting and Markdown preview.

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

Rename project conversations into clear, content-based Category｜Topic titles.

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration.

LESSONS.md (AI mistake notebook) visualizer panel for DeepSeek Harness Web UI — browse, search and review your AI mistake notebook entries by level and recurrence.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Native headless and visible Chromium browser automation agent for DeepSeek Harness with DOM tree extraction, screenshot capture, and built-in SSRF protection.

Persistent long-term memory for DeepSeek Harness: a JSON store of typed entries (fact, preference, entity, rule, episodic) exposed as the memory_remember and memory_recall agent tools, with recall ranked by keyword overlap, importance and access frequency.

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

An Agent-safe context compressor for DeepSeek Harness. It semantically preserves critical tool outputs such as errors, file paths, JSON payloads and command results, instead of mechanically truncating the context.

Deny an AI agent access to .env files, credential stores, keys and any path you hide — across file tools, shell commands, search selectors and run_code. A DeepSeek Harness (dsh) plugin.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

在 DeepSeek Harness 对话中以会话级 artifact 安全展示交互式 HTML 可视化。

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

flykit for DeepSeek Harness — status line, file explorer with editor and live watch, and Claude Code / Pi / Codex terminals in the web GUI. Fly your agents.

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.