플러그인

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

iPolloWork HyperFrames Video Studio and 27 editable video 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.

Bridges DeepSeek Harness lifecycle status, errors, and approval requests to a locally running OpenPets desktop companion.

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

모든 모델에서 사용 가능한 오픈소스 CMA 호환 에이전트 런타임으로, MCP 도구, 샌드박스 세션, 감사, 리플레이, 로컬 콘솔을 제공합니다. stdio MCP 기반의 네이티브 DeepSeek Harness 번들을 포함합니다.

AI 에이전트를 위한 LLM 감독형 영구 메모리로, 그래프 기반 회상, 세션 간 지식 공유, 단일 바이너리를 특징으로 합니다. DeepSeek Harness, Claude Code, OpenClaw 등 모든 에이전트 런타임과 함께 작동합니다.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

커뮤니티 배포판: TUI, 데스크톱, Web UI를 계층형 설치로 하나의 번들에 담았습니다.

PLUR memory for DeepSeek Harness — engrams injected straight into the prompt, no tool call required

嘉立创EDA专业版(EasyEDA Pro)自动化：给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作，CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱，以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.

DSH 플러그인 마켓플레이스: DeepSeek Harness Web GUI에서 GitHub topic:dsh-plugin의 모든 플러그인을 원클릭으로 탐색, 설치, 업데이트합니다.

Desktop feature aggregate that installs the DSH Web UI collection, dshmarket, Codex Connect, and reasoning-effort controls at pinned versions.

Base aggregate for DeepSeek Harness Desktop features: Web UI collection, plugin market, Codex Connect, and reasoning controls.

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

Profile-wide DSH governance and routing bundle with configurable compaction calls and scoped local semantic memory; compatible with DSH 0.1.0-rc.6 and 0.1.0-rc.7.

Sealos용 AI 에이전트 스킬로, 명령 한 번으로 모든 프로젝트를 배포하고 데이터베이스·오브젝트 스토리지 등을 프로비저닝합니다. Claude Code, Gemini CLI, Codex와 함께 사용할 수 있습니다.

13종의 코딩 에이전트(Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode 등)에서 완전한 형태의 대화 기록을 가져와 재개 가능한 DeepSeek Harness 세션으로 만들고, Claude Code로 역으로 내보낼 수도 있습니다.

동일한 작업에 대해 여러 스킬을 비교하여 최적의 결과를 선택합니다.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

QR 코드 스캔으로 IM 봇을 DeepSeek Harness에 연결(Feishu, Weixin, DingTalk 등 지원)