DeepSeek Harness Plugin Leaderboard
Install-verified DSH plugins, ordered by GitHub stars.
OpenViking memory and context bundle for DeepSeek Harness.
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
Opt-in DeepSeek Harness Skill-only bundle for the Archify architecture-diagram skill.
DSH Desktop: an Electron shell composed as a DeepSeek Harness Cordis plugin.
Mount Ouroboros (spec-first AI dev workflow engine) into DeepSeek Harness as native tools — type "ooo interview" or "ooo auto" in chat.
iPolloWork Design Studio and its curated design templates as a native DeepSeek Harness conversation view.
Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.
Plugin and skin collection for the DSH Web UI: task board, Git graph, right-side panel, remote mobile UI, pet, live token stats, and a skin center.
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.
Claude Code-style full-screen terminal UI: pixel-whale header, live status line, and streaming thought expansion.
Whale-girl skin series for the DSH Web UI (maid-atelier).
AgentRQ task manager for DeepSeek Harness: create, manage, and auto-pull AgentRQ tasks without leaving the harness.
Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.
Live model working-status line: playful copy, running tool, turn elapsed — for TUI prompt and Web UI.
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
(Recommended) The plugin market inside DSH: a Settings page to browse and search the full community catalog by category, with confirmed one-click installs and an installed-plugins view.
Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.
Install the full dsh-mnemon integration from the Mnemon repository.
Parody ads in 2005-Chinese-web style: sidebar banners, in-chat feeds, corner popups, and a close button whose hit area is smaller than it looks. All fictional.
Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.
Design skill for UI and marketing graphics on the Superdesign canvas: reads the repo for context, extracts its design system, then generates and iterates branchable design drafts, flow pages, and reusable components through the Superdesign CLI.
AgentTeams multi-agent teams.
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.
HarmonyOS NEXT skill bundle for DeepSeek Harness.
Codex-style `@file` mentions: search workspace files in the composer and attach their contents to prompts.
Community distribution: TUI, desktop, and Web UI as one bundle with layered installation.
Desktop pet (QQ-pet style): floats in the corner, draggable, feedable, playable.
A terminal UI (TUI) for DeepSeek Harness.
In-conversation generative UI: the model renders interactive HTML cards into the chat stream, with streaming preview and sandboxed rendering.
Curated file-based long-term memory for DeepSeek Harness — discovery manifest for the installable plugin in adapters/dsh/plugin/.
DSH-Transparent-UI-Plugin: a highly customizable glassmorphism theme for the Web surface — adjustable blur, frost, fluid or wallpaper backdrop, unified corners, and motion.
DeepSeek Harness 插件:把用户对话导出为锤子便签(通过便签服务 API 写入云端工作区)。
Interactive UI components rendered inline in replies: layout, charts, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model.
DeepSeek Harness plugin: installs the 'minimal-gitbash' agent preset — the Windows variant of the shipped minimal preset that routes the bash tool through Git for Windows bash (MSYS), with automatic shell discovery and sandbox-aware gating.
Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).
Context insight panel: see what the model's context window is made of and how it evolves — composition vs. window size, per-request history, compression/injection events, and per-message token stats.
DeepSeek Harness 插件:对话内多源搜番,卡片详情与磁力复制
Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek) and rewrites the text into natural prose on request; 39 regex markers with an evidence registry, offline, text-only bundle.
OpenPencil design preview and editing plugin.
Search built for agents: multilingual coverage across web, academic, code, shopping, finance, news, and encyclopedias.
GitHub-topic-driven plugin & skill marketplace: a Settings page that browses the auto-collected registry (the whole dsh-plugin topic plus the skills index, CI-refreshed every 2 hours) with one-click install, type detection, install-script and host-shadow-dependency safety confirmations, env-key management, and the STANDARD.md recognition spec.
Code review assistant for DeepSeek Harness: code_review_context collects deterministic git diff context; a bundled skill drives the review checklist.
Profile-wide odai governance and routing bundle for DeepSeek Harness.
Fail-closed automatic permission policy for DeepSeek Harness.
Co-Engram team memory plugin for DeepSeek Harness (dsh): native Cordis tools + dynamic prompt-signals injection.
Day/night whale-girl skin: a crystal workshop by day and a moon-tide observatory by night, with paired scenes, chibi companions, ornaments, and lightweight bubble and star ambience.
Compare multiple skills on the same task and pick the winner.
KodaX-parity dynamic workflow harness for DeepSeek Harness.
Using DSH and plugins
What is DeepSeek Harness?
DeepSeek Harness, or DSH, is DeepSeek AI's open-source agent harness. It uses an everything-is-a-plugin architecture powered by Cordis and is currently a developer preview.
How do I run DSH?
Install Node.js, then run npx @deepseek-ai/dsh web. The Web UI starts at http://127.0.0.1:3080 by default.
What is a DSH plugin bundle?
A distributable plugin bundle declares dsh.bundle.patch in its package.json. The patch contributes one configuration layer to a DSH profile.
How do I install a plugin?
Use dsh plugin --profile web add <package-or-github-spec>. Compatible plugin pages show the exact installation command.
How is DSH compatibility checked?
CI first checks dsh.bundle.patch, then runs the exact dsh plugin addcommand in an isolated profile. Successful installs rank first; manifest-confirmed bundles remain available with a lower compatibility score while verification is pending.
Are DSH Web's built-in plugins ranked?
No. The Web profile already ships with @deepseek-ai/dsh-base and @deepseek-ai/dsh-web-app. Both are official bundles and are excluded from the third-party leaderboard.
Is it safe to install plugins?
Verification confirms the manifest format, not that third-party code is safe. Review the source, pin a commit, and only allow install-time build scripts for repositories you trust.
How is this leaderboard ranked?
Each GitHub repository occupies one rank, even when it contains multiple bundles. Only repositories that pass an isolated dsh plugin add run receive a rank; GitHub stars decide their order.