629 results
DeepSeek Harness plugin: the agent publishes a project plan (steps) and a project framework (architecture graph); the browser renders the steps in a right-hand panel and the framework as a downloadable diagram in the center view.
Installable DSH bundle and remote companion for mobile access
End-to-end encrypted mobile approval companion for DeepSeek Harness
Trace DAG visualizer for the dsh web GUI: a conversation view tab that projects the official trajectory snapshot into a ReactFlow trace graph with dagre / d3-force layouts, hover highlighting, and a slide-out detail panel.
DSH Web UI plugin: check your DeepSeek API key balance/quota (GET /user/balance) from the sidebar, with a GUI panel showing total/granted/topped-up balance.
DSH web plugin: unified Git + GitHub + workflow + files panel (branch, stage/unstage, diff, commit, push/pull/sync, log, files, GitHub OAuth full access, workflow board).
DeepSeek Harness mobile pairing remote plugin: E2EE companion over a dual-plane allowlisted RPC (LAN / Tailscale / optional Cloudflare Quick Tunnel or self-hosted rendezvous).
DSH bundle plugin: a petdex.dev companion-pet market in the Settings UI with a native macOS desktop pet. Browse, search, install, enable, rename, and delete pets; previews are proxied same-origin to dodge CORS.
DSH web GUI scheduled-tasks panel: manage DSH agent reminders and system crontab entries from a sidebar panel with full-screen detail editing.
DSH settings panel for viewing and managing ~/.agents/skills and per-project .agents/skills skill directories
OpenTelemetry traces backend for the DeepSeek Harness telemetry seam: folds agent session events into OTLP span trees
A DeepSeek Harness client plugin that mirrors the current conversation into an independently scrollable details panel.
DSH Web UI 多語言插件：新增繁體中文/日本語/한국어/Français/Deutsch/Español 語言選項，官方介面字串逐條精譯，英文內容保持英文
Mobile / small-tablet UI optimizer for the DeepSeek Harness Web GUI: drawer sidebar, full-screen settings sheet with top tabs, bottom-sheet details panel, safe areas, and touch-friendly targets — all behind a max-width:820px breakpoint.
Pastoral cottage skin for the DSH web GUI: full-screen wallpaper with frosted-glass panels
Black hole theme plugin for the DeepSeek Harness Web UI: WebGL Schwarzschild black hole background with deep-space glass panels, switchable from Settings > General > 主题-黑洞. Install into a web profile: dsh plugin --profile web add <path-to-this-package>
DeepSeek Harness (cordis) client plugin: a right-side session stats panel showing average cache-hit rate, session cost, runtime, request count and cumulative tokens (DeepSeek pricing).
Line-anchored read/edit/batch_edit/grep/undo_last_edit tools for DeepSeek Harness (dsh). Every line is addressed by `<line>:<anchor>` so chained edits skip a re-read; stale or ambiguous anchors are rejected and a fresh `<line>:<anchor>` is served back. Undo persists across restarts. Ships a companion web client half rendering hashline-branded read/edit cards.
Jarvis blue-tech HUD skin for the DSH web GUI: deep blue-black palette, ice-cyan neon tokens, glass panels, HUD corners, and a breathing J.A.R.V.I.S. watermark that answers FOR YOU, SIR, ALWAYS while the agent thinks.
Git panel for DeepSeek Harness: log timeline, branch and worktree management over registered workspaces
微信读书 (WeChat Reading) integration for DeepSeek Harness: connect the official WeRead Skills Agent Gateway with a wrk- API key, then browse your bookshelf, export highlights & thoughts, query reading stats, and send highlights to flomo — agent tools plus a web settings panel
DSH web plugin: Codex-style /side side conversations. Open a temporary fork of the current chat in a floating panel — ask side questions without interrupting the main task or polluting its context.
Auto-expand every Think row, including after switching sessions. Header switch to turn it on or off.
DSH Web plugin: a right-docked file panel that browses any directory and views/edits text, images (brightness/contrast/grayscale/rotate/flip), and Office/PDF documents (.docx/.xlsx/.pptx/.pdf via local Python).