VisionPower

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

RunhuaHuang/VisionPower

View on GitHub ↗

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

VisionPower grew -4.3% in the last 30 days, ranks 2287th of 2,447 in Protocols (MCP / A2A), last commit 64 days ago.

Star trajectory

82 days tracked
2026-08-3166 stars today2026-11-22
Momentum

-4.3% in 30d, below the Protocols (MCP / A2A) median of +1.8%.

Maintenance

Last commit 64 days ago, staler than the median of 12d.

How it compares in Protocols (MCP / A2A)

VisionPower
66
stars
-4.3% 30d
commit 64 days ago
Protocols (MCP / A2A) median
223
stars
+1.8% 30d
commit ~12d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 2287th of 2,447 by stars.

Ranked by shared tags, then keywords, then stars
  1. Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender…

    +3.2k (+10%) in 30d · Committed 3d ago · Python · MIT

    Shares Protocols (MCP / A2A), Tools & Integrations, Voice / Vision I/O

  2. Reference architecture for agentic AI chatbots with Strands Agents and Amazon Bedrock AgentCore

    +7 (+3.6%) in 30d · Committed 5d ago · Python · MIT

    Shares Tools & Integrations, Protocols (MCP / A2A), Voice / Vision I/O

  3. 多模型视觉理解 MCP 服务器,为不支持图片理解的 AI 编码模型提供视觉能力:分析截图、报错、UI 与文档,可接入多家主流视觉大模型。Multi-model vision MCP server that adds…

    +0 (+0.0%) in 30d · Committed 105d ago · TypeScript · MIT

    Shares Protocols (MCP / A2A), Tools & Integrations, Voice / Vision I/O

  4. 给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard…

    +0 (+0.0%) in 30d · Committed 54d ago · Python · MIT

    Shares Protocols (MCP / A2A), Tools & Integrations, Voice / Vision I/O

  5. A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

    +1 (+2.3%) in 30d · Committed 65d ago · TypeScript · Apache-2.0

    Shares Protocols (MCP / A2A), Voice / Vision I/O, Tools & Integrations

  6. AIHawk: AI job application bot, automated job search, job hunting, auto-apply to resume-matching jobs while…

    +382 (+1.2%) in 30d · Committed today · Python · MIT

    Shares Tools & Integrations, Voice / Vision I/O, Protocols (MCP / A2A)

  7. An enterprise collaboration platform for people and multi-agent teams, built on the open-source DeepSeek…

    +350 (+4.9%) in 30d · Committed yesterday · TypeScript · Other license

    Shares Tools & Integrations, Protocols (MCP / A2A), Voice / Vision I/O

  8. Sound effects for coding agents: ask in plain words and earshot renders the sound in code. CPU-only, no audio…

    +3.3k (+145%) in 30d · Committed today · Python · MIT

    Shares Voice / Vision I/O, Protocols (MCP / A2A), Tools & Integrations

  9. Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.

    +11 (+0.9%) in 30d · Committed 5d ago · TypeScript · MIT

    Shares Voice / Vision I/O, Tools & Integrations, Protocols (MCP / A2A)

  10. Local-first visual generation runtime and studio for people and coding agents, with reproducible image and…

    +21 (+2.4%) in 30d · Committed yesterday · TypeScript · MIT

    Shares Voice / Vision I/O, Tools & Integrations, Protocols (MCP / A2A)

Language
JavaScript
License
MIT License
Contributors
4
Forks
8
Watchers
0
Open issues
1
Releases
25
Created
2026-06-19
Stars this week
-2

You've seen where VisionPower stands today.

Get the moves before everyone else: the 5 Protocols (MCP / A2A) repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain VisionPower?

Claim this page to add your own call-to-action.

Claim this page