3731 results
Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, and what a change reaches, from a tree-sitter index it builds itself. Compatible with the codegraph CLI's on-disk format.
Miraculous Standard — unified anchored agent preset for DeepSeek V4 Pro/Flash (official API & opencode-go). Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, unified context gate, epoch-aware catalog management, rc7-ready shell handling.
DeepSeek Harness bash executor plugin that routes eligible commands through rtk (Rust Token Killer) to compress tool output and save tokens. Optional overlay: install, then enable via --patch.
从规划到发布的 DeepSeek Harness 插件全流程指南，覆盖需求与形态决策、脚手架生成、业务实现、本地验证、发布准备和最终发布。Use when the user wants to plan, create, bootstrap, develop, verify, or publish a DSH plugin/extension, or asks how to build a DeepSeek Harness plugin end-to-end.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
Agent teams for DeepSeek Harness: named long-lived teammates over ctx.subagents, a shared task list, a member-to-member mailbox, virtual workspaces, and an interactive voxel world in the conversation view
Archived sessions viewer for DeepSeek Harness: list archived conversations and restore them from the Web settings — no DSH core is modified.
Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.
Unofficial Plannotator integration for DeepSeek Harness: annotate plans inline and return structured feedback to the waiting coding agent
DeepSeek Harness Web 可扩展回答状态宠物框架：支持宠物主题、多会话进度、模型轨迹和工具调用。
Route DeepSeek Harness model-API requests through an HTTP/SOCKS proxy without modifying Harness source
在 DSH web 界面自动展开工具调用卡片，支持侧边栏开关。标准可安装的 dsh 客户端插件。
Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)
Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
Windows-first bash tools for DeepSeek Harness: git_bash (Git Bash) and wsl_bash (WSL2) model tools with bwrap sandbox, approval mode, terminal-style UI cards, and background-job support
WaLiOffice 办公工具套件 — DeepSeek Harness (DSH) 插件
自进化插件：agent 在 session 内随对话按需给自己长出/剪掉能力 —— evolve_add 把 cordis 插件源码落盘并热挂载（下一 step 工具即可见），evolve_remove 可逆卸载，重启自动恢复
DeepSeek Harness (DSH) 主题体验插件：OKLCH 主题提案 + 主题设计器（独立色相/彩度/明度通道、通道锁定、配色关系与快速变体、AI 命名、JSON 导入导出），并放大设置面板宽度。作为 web 插件热插拔安装，跨重启保留。
DeepSeek Harness plugin: paragraph-batched streaming reveals with 8 designed animations, smooth scroll-follow and a settings panel.
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
Replace dsh's built-in web search with search MCP servers (Tavily / Brave / Exa / Perplexity / DuckDuckGo / custom), configured from the web Settings page. When this plugin is enabled the built-in DeepSeek search provider is disabled.
Clickable file paths in DSH replies: open files/directories from inline paths (Codex-style), with a mentioned-files chip list as fallback
A DeepSeek-style paperclip attach button in the DSH web composer; uploads files to the DSH host (model-aware: native image blocks for multimodal models, file paths for text-only models).