v0.8.5 · Apache-2.0
DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.
v1.1.2 · MIT
DSH 个人配置:Token 用量统计 / 成本估算 / 自定义指令 / 外观全局字号 / 桌面宠物(含会话状态概览),纯本地不联网。Personal center for DSH: usage stats, cost estimation, custom instructions, global font size & desktop pet with session overview — all local & offline.
v0.1.2 · MIT
Near-native image understanding for DeepSeek Harness
v0.8.2 · MIT
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
v0.2.22 · MIT
Interactive in-browser canvas for real-time preview of HTML, React components, SVGs, and diagrams with SSE hot-reload
v2.0.2 · MIT
Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system
v0.5.11 · MIT
DeepSeek Harness companion for ClineBot / ClinePass: dynamic subscription models sync, quota exhaustion warnings, session metrics, dedicated settings page, live usage limits, and /cline slash-command.
v2.0.2-alpha · MIT
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
v0.14.6 · MIT
DSH 邮件插件:IMAP/SMTP 收发搜索、回复转发、附件与整理,多账号卡片设置页、Outlook OAuth2 登录与发信审批。
v2.3.0 · MIT
DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活:迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.
v0.3.2 · MIT
Claude Code plugin that transforms vague requirements into detailed implementation plans via research, interviews, and multi-LLM review.
v0.4.32 · MIT
Retrace · 回溯 — Recall, edit-and-resend, regenerate, and conversation/artifact versioning (timeline, rollback, fork map) for DeepSeek Harness — Web and Desktop
v0.16.0 · MIT
Login gate for DeepSeek Harness (dsh) web instances: password or shared-token sign-in, optional TOTP two-factor, session cookies, rate limiting, self-service password change and a user-management CLI
v0.8.15 · MIT
A library for patching, replacing and decorating DeepSeek Harness plugins during runtime
v2.0.0 · MIT
Excalidraw toolkit for AI coding agents — agent skill, CLI, and MCP server with a live canvas
v1.3.4 · MIT
Reverse-engineer design systems from any website, repo, or project. Extracts colors, fonts, spacing, animations, and components - packaged as a .skill file for Claude. Pure static analysis, zero AI, zero API keys.
— · no license
Video-making skills for Claude Opus 5.5 in Claude Code — every frame and note generated in code, one skill per style: hand-painted animation, kinetic-typography reels | 用 Claude Opus 5.5 以代码制作视频的技能合集
v0.19.0 · MIT
L0~L3 分层蒸馏记忆插件 for DeepSeek Harness:自动捕获对话(L0)、抽取原子记忆(L1)、整合场景块(L2)、蒸馏核心画像/团队方法论(L3),并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。
v0.1.25 · MIT
DSH plugin for smart checkpoints, workspace safety guards, and instant rollback
v0.0.7 · BSD-3-Clause
Lark/Feishu IM bot channel for DeepSeek Harness | 飞书 DeepSeek Harness (DSH)插件
— · MIT
Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.
v0.16.0 · MIT
Superpowers & Beads task memory for AI coding agents - supports Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Kimi Code, Antigravity, Factory Droid, and Pi.
— · Apache-2.0
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
— · Apache-2.0
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.