v1.7.7 · MIT
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
v0.1.39 · MIT
[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
— · MIT
为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
v3.24.2 · MIT
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
v1.0.0 · MIT
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
v3.24.2 · MIT
Plug-in vision for text-only LLMs, powered by the free Antigravity CLI
v0.2.7 · MIT
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
v0.4.0 · MIT
Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。
v1.0.0 · MIT
Recreate any web animation from a screen recording. A motion-design plugin: analyzes motion (timing, easing, stagger, loops) and rebuilds it as GSAP / CSS / Framer Motion / Lottie code.
v0.0.1 · Apache-2.0
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
v0.2.0-alpha.4 · MIT
Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.
v0.3.1 · MIT
Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.
v3.1.1 · MIT
DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
v2.67.2 · MIT
Workflow-continuity bridge for AI coding agents. Wrap Claude Code or Codex in a PTY and supervise, approve, and redirect the session from any device — async. The terminal companion for CodeAgent Mobile.
— · MIT
Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)
v1.0.0 · MIT
agentic skills for apple platform engineering
— · no license
The most advanced, fully offline client-side AI suite on Android today.
v0.1.2 · MIT
Chrome sidebar extension that lets DeepSeek Harness operate your browser directly, no vision capabilities required. 一款 Chrome 侧边栏扩展程序,可让 DeepSeek Harness 直接操控您的浏览器,无需视觉能力。
v0.1.0-rc.6 · MIT
DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.
— · MIT
Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.
v1.2.5 · no license
AI agent skills for Sealos — deploy any project, provision databases, object storage & more with one command. Works with Claude Code, Gemini CLI, Codex.
v0.10.1 · MIT
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.
v2.9.0 · MIT
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
v1.0.3 · MIT
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow