Rank #5,289 1,234 starsPython

agent-vision-toolkit

by Anionex (personal account)

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 (description from the project’s GitHub page)

View on GitHub Homepage

Repository facts

Stars: 1,234
Forks: 50
Open issues and pull requests: 8
Primary language: Python
License: MIT License (MIT)
Owner: Anionex · Personal account
Created: Aug 1, 2026
Last push: Oct 13, 2026

Topics

Rank #5,289 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Projects that share this one’s GitHub topics.

Rank 1,855: liustack/modlens
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…
4,309 starsTypeScriptMITLast push Oct 15, 2026
Rank 7,434: liustack/modsearch
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get s…
744 starsTypeScriptMITLast push Oct 18, 2026
Rank 2,643: Tiger3807861189/J-Space-Cognition-Suite
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 work…
2,974 starsPythonApache-2.0Last push Sep 14, 2026
Rank 2,825: zilliztech/memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
2,758 starsPythonMITLast push Oct 9, 2026
Rank 6,543: Anionex/dsh-vision-toolkit
[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,…
898 starsTypeScriptMITLast push Oct 18, 2026
Rank 3,988: zhnt/loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude…
1,797 starsPythonApache-2.0Last push Oct 18, 2026

Repository facts

Topics

Related projects

Rank 1,855: liustack/modlens

Rank 7,434: liustack/modsearch

Rank 2,643: Tiger3807861189/J-Space-Cognition-Suite

Rank 2,825: zilliztech/memsearch

Rank 6,543: Anionex/dsh-vision-toolkit

Rank 3,988: zhnt/loushang

Support Us