A tiny local web app that sends the same prompt to Claude, Codex (GPT), and Antigravity (Gemini) via their CLIs, displaying responses side-by-side without needing API keys.

Stars

75

7-day growth

No data

Forks

9

Open issues

0

License

No data

Last updated

2026-07-25

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It leverages existing CLI subscriptions and requires no API keys, enabling side-by-side comparison of three major AI models with minimal setup and zero dependencies beyond Node.js.

Who it is for

  • Developers subscribed to multiple AI services
  • AI enthusiasts wanting to compare model outputs
  • Privacy-conscious users who prefer local execution
  • Writers or researchers using AI for idea generation

Use cases

  • Comparing answers from Claude, GPT, and Gemini on the same prompt
  • Brainstorming with diverse AI perspectives simultaneously
  • Testing model consistency or differences in reasoning
  • Fact-checking or augmenting responses across multiple AIs

Strengths

  • No API keys required – uses existing CLI subscriptions
  • Zero dependencies (pure Node.js server) with concurrent execution
  • Supports images, conversation memory, model switching, and bilingual UI
  • Built-in security: localhost binding, restricted working directory, no shell injection

Considerations

  • Requires installing and logging into three separate CLIs (Claude Code, Codex CLI, Antigravity)
  • Image support for Claude and Antigravity is indirect (path injection in prompt)
  • Designed primarily for macOS (brew instructions) and assumes CLI availability

README quick start

使用

Description

🦊 Ask once, get three answers — same prompt to Claude / Codex (GPT) / Antigravity (Gemini) via their local CLIs

Related repositories

Similar projects matched by category, topics, and programming language.

ddosi
Featured
ddosi GitHub avatar

PacketLens

PacketLens is a pure front-end, offline pcap analysis tool that runs entirely in the browser, supporting deep protocol decoding, HTTPS decryption, and million-packet instant loading without any backend.

HTML
17
ViffyGwaanl
Featured
ViffyGwaanl GitHub avatar

kimi-k3-learn

An interactive learning system that turns the 47-page Kimi K3 technical report into a single offline HTML file with running algorithms, 3D visualizations, spaced repetition quizzes, and a smart highlighting QA tool.

AI & Machine Learning
15
iamtechartist
Featured
iamtechartist GitHub avatar

human-cell-visualizer

An interactive 3D visualization of three human cell types using Three.js, WebGL particles, and custom GLSL shaders, allowing users to rotate, zoom, morph, and explore annotated structures.

Design & Creative
13