Plugins
Browse, filter, and install DeepSeek-Harness plugins.
99 plugins found
auto-claude-code-research-in-sleep
wanshuiyin/auto-claude-code-research-in-sleep
ARIS research-workflow skills as a DeepSeek Harness bundle: 82 skills plus cross-model adversarial review through Codex.
Study-Mate
miaotofu01/study-mate
Your AI learning companion: helping you plan your studies, understand concepts, and build projects to master a subject.
dsh-memory
furongjun-1999/dsh-memory
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
bloomtutor
li-evan/bloomtutor
Open-source AI tutor for personalized learning: Socratic, adaptive lessons to learn anything. Claude Code skill + self-hosted web app. Bloom 2 Sigma · 开源 AI 家教
agentdescent
birfy/agentdescent
Evolve skills, agents, prompts, code and plugins from inside DeepSeek Harness, with AgentDescent.
dsh-run2skill
qkycir-123/dsh-run2skill
Turns explicit DSH session experience into reviewable native Skill drafts that are saved only after user approval.
dsh-reforge
wang1299/dsh-reforge
DSH-Reforge (dsh-reforge) — DeepSeek Harness plugin for traceable experience from test-verified Python bug fixes. 从有测试依据的 Python 修复中积累可追溯经验。Experimental alpha · DSH 0.2.0-rc.2 / 0.2.1-rc.5.
qiaomu-ui-learn-dsh
joeseesun/qiaomu-ui-learn-dsh
Browse UI design references and interaction examples, take design quizzes, and export learning notes as Markdown.
CiteCiter (citeciter)
kirkchinese/citeciter
Select text in a committed DSH response to open an independent, persistent, read-only multi-turn Topic bound to source-session evidence and project files while the source Agent keeps running.
oss-prompt-optimizer
seven282/oss-prompt-optimizer
One-click optimization of a raw instruction into a professional prompt: three output styles, situation-aware role/task/goal profiling, multi-sample selection scored by a model judge, self-iterating learning (session memory + smart defaults + user overrides), /template for 22 sub-scenes with zero model calls, input-box ✨ one-click optimize/undo, prompt_optimize tool, auto-optimize hook, a runtime status page, a settings panel (dsh 0.2.0) and auto-detected zh/en documents.
dsh-plugin-lookatstudy
kaiji-z/dsh-plugin-lookatstudy
A study tab with course-map, tutor and blackboard columns that turns markdown files, local folders or GitHub repos into guided courses, with lesson unlocking, mastery tracking, spaced repetition and a tutor-designed course import.
dsh-qfish
hyun20202023-ui/dsh-qfish
Unofficial QQ bot plugin for DeepSeek Harness (requires a NapCat/OneBot v11 endpoint): editable persona, per-user memory with condensing, session rotation with summaries, image and Bilibili video understanding, sticker library, slang and catchphrase learning, favorability, group management, reminders, cross-group messaging, and a built-in web console. Default-deny: replies to nobody until QQ user and group allowlists are configured. Derived from dsh-onebot; cannot be installed together with dsh-onebot (both register /onebot/api and answer the same NapCat). Video frame grids need ffmpeg on PATH.
dsh-continual-harness
jasen215/dsh-continual-harness
Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.
dsh-explain
yuezengwu/dsh-explain
Local-first learning mode: cross-session learning threads with per-source explanations.
dsh-feed-the-seek
morgiana-v3/dsh-feed-the-seek
Personal cross-session memory in local SQLite, with automatic conversation learning, companion states, and optional semantic retrieval. Currently intended for single-user local use on Windows.
dsh-explain
dsh-external/dsh-explain
Learning mode that explains each agent step (WIP).
dsh-learning-mode (plugin)
chplus0/dsh-learning-mode
Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).
dsh-deeptutor
tecfancy/dsh-deeptutor
DeepTutor tutoring bridge: deep explanations, self-test questions, learning-path planning, personal knowledge-base search (RAG), and note archiving via deeptutor_run / deeptutor_kb / deeptutor_note tools.
dsh-brainagent
stas130286-blip/dsh-brainagent
Brain-inspired cognitive plugin: episodic, semantic, procedural and emotional memory with reinforcement-learning signals, a goal stack with time triggers, curiosity-driven autonomous web research and proactive initiatives.
docs-mode
zh851233/docs-mode
Technical documentation agent preset for DeepSeek Harness: template-driven writing with a self-learning template library, AI-flavor removal for tech docs, and a quality-assurance toolkit (document audit, cross-document consistency, numbering resequencing, version sync, PDF and Word export, screenshot automation).
evo-subagent
zekaishi/evo-subagent
Smart subagent routing and evolution: bind roles to any provider/model registered in DSH, including models supplied by Codex and Claude Code provider plugins, with workspace learning.
dsh-talent-tree
a961282799-crypto/dsh-talent-tree
A learning talent tree: give it a topic and the agent splits it into a prerequisite graph of knowledge points, each with a hook (the one formula, idea or question that makes it interesting), a plain-language summary and a symbol glossary; a point lights up bronze, silver or gold only after you explain it in your own words or answer a check question correctly. Adds a left-sidebar overview of every goal, a pannable and zoomable tree with learning routes and a recommended next point, a skip-ahead challenge, a due-review queue, light-up animations, KaTeX-rendered formulas and PNG export.
dsh-aha-tutor
baroncyrus/dsh-aha-tutor
开窍 Aha Tutor: a personal AI tutor for DeepSeek Harness that builds a course around you and teaches it on a narrated handwriting whiteboard
dsh-perm-gate
drscrewdriver/dsh-perm-gate
Shipped with cc-safety-net-style mechanical safety-net rules appended; supports both no-model and model-assisted security review, in modes such as 自动审查 (auto-review) and 机械直通 (mechanical pass-through). P0–P4 deterministic-first permission gate with permissive tier, learning sedimentation and approval-history UI; hard-deny credentials and protected paths, auto-allow internal read-only tools.