v0.1.3 · MIT
❤️ Generate mermaid diagram and chart with AI MCP dynamically.
v1.1.0 · MIT
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
— · MIT
🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.
— · Apache-2.0
Drive the Pi coding agent from Claude Code or Codex: multi-model review panels, model racing, incremental & sharded reviews, automatic model fallback, /pi:rescue with parallel subagent fan-out. Any provider (DeepSeek/OpenAI/Anthropic/local). Adapted from codex-plugin-cc.
v0.1.3 · MIT
Desktop notifications for DeepSeek Harness turn completions, with per-outcome controls and include/exclude keyword rules.
v0.1.31 · MIT License
Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.
v0.1.39 · MIT
An independent, open-source desktop wrapper for DeepSeek Harness. It starts the bundled @deepseek-ai/dsh Web UI locally and loads it in a hardened Electron window on Linux, macOS, and Windows.
v1.2.2 · MIT
Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding
v0.1.0 · MIT
Advanced per-model reasoning and capacity settings for DeepSeek Harness
v0.1.6 · MIT
Open DeepSeek Harness workspace directories in VS Code directly from the web GUI.
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
v1.0.1 · MIT
Measured share of answer for 24 crypto and Web3 brands. An open dataset, not an audit of your site.
v1.0.0 · MIT
Film stills from 5,489 films, searchable by lighting, lens character, shot size, colour and mood.
v0.1.0 · BSD-3-Clause
dsh-IDE 把 DeepSeek Harness(DSH)网页版升级成一站式 IDE:JupyterLab 式文件树、带语法高亮的代码编辑、多格式预览、Trae 风格红绿 diff 和内置终端,再加上「本地大脑、远程手脚」的 SSH 远程工作区,让 AI 直接在本机操控远程服务器,全程零配置文件改动。
v0.1.2 · MIT
Create and manage sandboxed JavaScript tools for DeepSeek Harness with a Monaco editor and model-driven tool lifecycle.
v0.2.0 · MIT
DSH 实现 workbuddy 同款选择 skill 功能 | WorkBuddy-style skill picker for DeepSeek Harness: pick a skill in the composer, insert the official /skill-name gesture, and DSH loads it with your message.
v0.5.3 · MIT
Run budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness, and return inspectable cited evidence.
v0.1.1 · BSD-3-Clause
DSH mobile-friendly web UI plugin (PiUI chat-pager mode): on narrow screens the stock three-column frame becomes a horizontal scroll-snap pager — sidebar | chat — with the chat column rendered completely untouched as a flush rounded card with a PiUI-style 3D flip; swipe or the top-left button flips pages, a settle re-snap always lands on a whole page, and the sidebar page shares the chat background. Safe-area + virtual-keyboard insets, touch-sized controls, hidden scrollbars on coarse pointers. Pure client-side adaptation over the stock frame — zero core changes, works on official rc.2 distributions.
v1.56.0 · Apache-2.0
Claude Code plugin & Agent Skills for AI-native development: codebase readiness scoring (/assess), Six Thinking Hats deliberation (/huddle), AI-slop removal (/deslop), skill hardening (/skill-forge), and more.
v0.2.0 · MIT
Claude Science-style research workbench for DeepSeek Harness: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), SSH remote-compute engine for long bioinformatics jobs on workstations/HPC (remote_* tools), and 11 science skills for genomics / pathogens / bioinformatics. Ships the tiered cross-provider model router via the companion dsh-model-tier bundle.
v0.8.0 · no license
DSH(DeepSeek Harness)插件:把 ego-lite 浏览器(给 AI Agent 用的 Chromium)接入 HARNESS——13 个结构化 ego_* 工具(文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离),内置 ego 运行时,Linux + Chrome 开箱即用,无需克隆官方仓库或手动构建。
v1.0.3 · MIT
Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,
v0.0.3 · MIT
Let Claude, Cursor, or ChatGPT author Mermaid diagrams your team can read and share.
— · no license
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.