103 results
MuseAI tavern for the dsh web GUI: a MuseAI conversation-view tab (right of Trajectory) with background / chat / adventure / bond / settings pages ported from MuseAI, running entirely on models configured in DeepSeek Harness (no separate API config)
Free web search for DeepSeek Harness: 12 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl keyless; Parallel/Perplexity/DeepSeek with key) + time filtering + platform search + web_fetch, with web settings UI.
Multi-engine fused web search, page fetch, real-time X (Twitter) search with credential-free fallback, deep research and parallel multi-agent research for DeepSeek Harness. Free layer: Bing / DuckDuckGo / Yahoo / Exa MCP (all keyless, live-probed); api layer adds Antigravity CLI and keyed Tavily/Brave/Exa.
DeepSeek Harness plugin: paragraph-batched streaming reveals with 8 designed animations, smooth scroll-follow and a settings panel.
DSH plugin: choose models for subagents and plan execution separately / 为子代理和计划执行选择更合适的模型
Settings UI for DeepSeek Harness (DSH) to edit each model provider's request retryPolicy — mode (normal/always), maxRetries, retryableCodes and exponential-backoff parameters — written to settings.yaml and applied by dsh-llm-retry. 模型重试策略设置：在设置面板中可视化编辑各模型提供方的 API 请求失败重试策略。
DeepSeek Harness plugin: per-event task-completion and attention sounds for turn-end / approval / question / plan-review / goal-blocked / task-failure, each with its own sound (built-in synth, local audio file) and volume, with a separate subagent channel (Web UI)
Give DeepSeek Harness agents live control of your ComfyUI canvas (local or cloud): embed it as a split-screen tab, then read/edit/run workflows, debug errors, fetch output images, and batch-sweep parameters straight from the chat. Ships the ComfyUI-side bridge node.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
DSH 免费网页搜索 provider + 设置开关（Parallel 默认 / Exa 备用）+ MCP server 双传输（stdio + HTTP/SSE），兼容 Claude Code / Codex，一键切换官方计费搜索与免费搜索
Write in parallel, never overwrite — file claim / protection for concurrent DeepSeek Harness (DSH) sessions working the same workspace: claim/release, heartbeat stale takeover, and an async pending merge area (git 3-way merge)
Wallpaper Engine integration for the dsh web GUI: scan the local Wallpaper Engine library (Steam workshop 431960 + local projects), use its wallpapers as the page background (image / video / web / scene-preview), and control them from a right-side '壁纸设计' panel (opacity, scope, fill, blur, vignette, fps, parallax, carousel, theme linkage). Agent tools wallpaper_scan / wallpaper_list / wallpaper_set / wallpaper_config.
Angelina light and dark glass themes with restrained parallax for DeepSeek Harness
novel-solo helper for DeepSeek Harness: a subagent-count setting (1-12) card in the Settings → Plugins panel, persisted to disk and consumed by the novel-solo preset to cap parallel subagent fan-out.
Floating notes for the dsh web GUI: keep commands, credentials, parameter values and other important snippets at hand while working, insert any note straight into the composer, and save any selected text (e.g. from an AI answer) as a note with one click
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
Engineering workflow layer for DeepSeek Harness (dsh): a disciplined-engineer agent preset with five gated phases — requirements clarification, plan approval, TDD implementation, parallel subagent execution, and verified finishing. Skills adapted from the obra/superpowers workflow methodology.
Professional Tavily-backed web search provider for DeepSeek Harness — full request parameters in a WebUI settings card, yaml-first priority, and API connectivity test
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK
Desktop pet for DeepSeek Harness Web UI: idle float animation, click speech, right-click settings panel, skin separation (assets + settings). Roadmap: alarm clock, sticky notes and more practical widgets — pure front-end.
TaskSwarm (蜂群) — multi-agent task orchestration for DeepSeek Harness. Native port of TaskPlane (github.com/HenryLach/taskplane, MIT): waves/lanes parallel execution, git worktree isolation, PROMPT.md/STATUS.md task packets, file mailbox, cross-model review.
DeepSeek Harness 原生并排侧聊：归档独立会话、按需主会话上下文、原生会话 UI 与可配置生命周期。
DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key — plus a composer badge showing subscription usage for those routes and for GLM Coding Plan.