플러그인

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

Connects DeepSeek Harness to OOMOL-managed apps and services, with progressive Connector Action discovery and execution plus an in-app panel for managing Provider connections.

명령 한 번으로 모든 프로젝트를 AI 에이전트가 다룰 수 있게 만듭니다. 적응형 기술 스택 감지(7개 언어 × 14개 프레임워크 × 61개 컴포넌트)를 수행하고 AGENTS.md, 문서 골격, CI/CD, 테스트 인프라를 자동 생성합니다.

Zed 등 ACP 클라이언트에서 DSH 에이전트를 완전히 사용할 수 있도록 하는 ACP 프로필 플러그인 및 독립 stdio 서버로, DSH 자격 증명과 세션을 함께 공유합니다.

조건 기반 웨이크업: 파일/명령/http/프로세스/웹훅을 영속적으로 감시하다가 조건이 충족되면 에이전트를 깨웁니다.

DSH↔Godot 엔진 런타임 브리지: 게임 내 TCP 상호작용 서버를 통해 실행 중인 Godot 4.x 게임을 실행하고 제어합니다 — 씬/UI 검사, GDScript 평가, 입력 시뮬레이션, 스크린샷, 헤드리스 정적 작업, 스크립트 검증까지 8가지 도구를 제공하며 godot-mcp를 대체합니다.

Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.

DSH Mini TUI: a minimalist terminal interface plugin for DeepSeek Harness

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").

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.

자기 진화 기능: 에이전트가 세션 도중 스스로에게 영구 플러그인을 핫마운트/제거할 수 있습니다.

Edit the global ~/.dsh/AGENTS.md rules from the web settings panel, live on save.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Chinese long-form screenwriting skill: two input blocks (background + character bible) feeding a causal-value engine, anti-AI-flavor review, and a continuity ledger; works on Codex / Claude Code / dsh / zcode.

Read any page as clean main content: charset auto-detect (GBK/GB2312/UTF-8/Big5), noise stripping, compact text/Markdown, offset continuation, optional SPA rendering, batch reads and site crawling.

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.

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.

역할 기반 LLM 재시도 및 폴백 전략입니다.

세션 간 메모리: 사람이 직접 편집 가능한 Markdown 미러를 갖춘 SQLite, 백그라운드 통합(중복 제거, 병합, 충돌 해결), 6가지 메모리 도구를 제공합니다.

기계가 읽을 수 있는 체크포인트와 낙관적 잠금(optimistic locking)으로 DeepSeek Harness, WorkBuddy, Claude Code, Codex 간에 영구적인 작업 상태를 이어갑니다.

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

Manages local DeepSeek Harness skills in Settings and shows shared Agent skills as read-only.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.