플러그인

dsh-compaction-audit용 Step-0 관찰 프로브: 모든 compaction/* 세션 이벤트를 기록하고 shadowedSeqs가 session.events에서 여전히 읽을 수 있는 이벤트로 해결되는지 프로빙합니다. 관찰 전용; 주입하지 않으며 차단하지 않습니다.

네이티브 이미지와 제한된 문서 읽기가 가능한 DeepSeek Harness용 사설 로컬 파일 첨부.

소스 줄 끝 보존과 구조화된 구문 강조 토큰을 기반으로 구축된 DSH 웹 플러그인용 이스케이프된 테마 인식 HTML 코드 블록 렌더링 서비스.

9가지 IM 봇과 공용 AI Office를 로컬 DeepSeek Harness에 연결합니다(Feishu, WeChat, DingTalk, Work WeChat, QQ, Slack, Telegram, Discord, WhatsApp 및 AI Office 지원). @xmanrui/dsh-im의 포크 — Feishu HTML 미디어 수정(private/custom).

휴먼 인 더 루프 도구(`human_task` / `human_task_ready_check`): 사용자가 실제 세계 행동을 수행하거나 관찰 결과를 반환할 때까지(GUI 조작, 게임 테스트, 시각 검증, 하드웨어 점검) 에이전트를 일시 중지하며, 세션 동의와 자리 비움(AFK) 존재 확인으로 제어되고, 웹 작업 대화상자를 통해 구조화된 JSON 결과를 반환합니다.

DeepSeek Harness 웹 설정용 향상된 플러그인 목록 — 신뢰 등급, 접을 수 있는 그룹 및 완전한 플러그인별 세부 정보

도구 결과의 자동 시크릿 마스킹: 모델이 보기 전에 API 키, 토큰, JWT, 개인 키, 설정된 시크릿을 가립니다.

채팅 이미지를 고정된 OpenAI 호환 비전 모델로 라우팅하고 사실에 근거한 관찰을 선택된 메인 모델에 반환합니다. 세션 범위 관찰은 리플레이·압축·재시작을 넘어 재사용됩니다.

anywhere-claude-mem의 git 동기화를 DSH 피어로 전환하는 DeepSeek Harness 플러그인: 세션 시작 시 여러 기기 간 메모리를 가져오고, 새 프롬프트/관찰 내용이 claude-mem worker에 도착하는 즉시 내보냄

Replaces the built-in bash executor so every command gets an environment resolved from its own working directory: configurable PATH prepends, Python venv activation and mise shims, with a dedicated section in the Web UI settings.

Pull invoice number, date, parties, tax IDs and the amount/tax/total triplet out of text, then verify that amount plus tax really equals the total and flag documents that do not reconcile.

Creates, activates, checks and removes external DSH plugins from a conversation through fixed tools; requires the external DSHX devkit.

TangSan mascot appearance layer for the DeepSeek Harness web GUI: wears a generated TangSan portrait as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/tangsan, and the config lives at $DSH_HOME/tangsan.json.

Nai milk-frog mascot appearance layer for the DeepSeek Harness web GUI: wears the bundled milk-frog artwork as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/nai, and the config lives at $DSH_HOME/nai.json.

MDSM (Male DeepSeek Mascot) appearance layer for the DeepSeek Harness web GUI: wears the bundled mascot character as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/MDSM, and the config lives at $DSH_HOME/MDSM.json.

Per-workspace activation control: a dialog opened from the workspace row menu switches individual plugins, MCP servers, and skills on or off, and the host applies the choice in that workspace's own agent scope — a disabled skill leaves the model catalog, an MCP server has its mcp__<server>__ tools denied, and a plugin has the tool names its entry declares denied.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Memory bridge between DeepSeek Harness and ai-memory: runs ai-memory's finalize-session when a DSH session ends, so the observations it already captured become searchable wiki pages. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart. Requires a separately installed ai-memory server with its DSH lifecycle hooks wired by hand — ai-memory’s own install-hooks does not support DSH; this plugin only finalizes what capture has already recorded.

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

Sync your DeepSeek Harness (DSH) configuration between machines over a private git or WebDAV channel: settings, plugins, MCP servers, skills, agent presets, workspaces and provider credentials. DSH 配置远程同步插件（私有通道，明文自用）。

33 github_* tools covering REST reads, issue writes, Git data writes, private repo creation, and clone; in-process permission gate and cost-discipline companion skill; no gh CLI required.

Insight dock for the DSH Web GUI: lets an agent park a short, strictly-bounded side observation while it works, shows it above the composer, and lets the user ask to hear it later — with a context anchor that survives context compaction.

DSH plugin: sync model settings, plugin manifests, patch layers and lockfiles across devices through a private Git repository (manual push/pull; https+token or ssh public-key auth).