The Pair

The Pair

Automated AI pair programming — two AI agents cross-check each other's code, so you can grab a coffee and come back to reviewed, validated work. _(Yes, The Pair was built by The Pair.)_

🌐 English • 简体中文 • 한국어 • 日本語  | 

macOS • Windows • Linux  |  ⬇ Download  •  CLI  •  🌐 Website

_Watch Mentor and Executor agents collaborate in real-time_

🎬 The 10-second launch film, autoplaying muted — watch the 4K60 original with sound

Table of Contents

- Overview — what The Pair is and why dual agents reduce AI hallucinations
- AI Search Summary — concise product facts for search and AI citation
- Why The Pair? — comparison vs. Cursor, Copilot, and single-agent tools
- Choose Your Interface — desktop app or terminal CLI
- Features
- Screenshots
- Installation — macOS, Windows, Linux
- Quick Start — install a provider CLI and create your first pair
- Configuration
- Architecture
- Development
- FAQ

Overview

The Pair is a free, open-source desktop app that runs two AI coding agents — a read-only _Mentor_ that plans and reviews, and an _Executor_ that writes code and runs commands — which cross-check each other's work to catch AI hallucinations before they reach your codebase. It runs locally on macOS, Windows, and Linux, and is model-agnostic: mix and match ten provider CLIs — opencode, Claude Code, Codex, Antigravity (Gemini), Kimi Code, Pi, Kiro, Aider, Grok Build, and Muse Code — in any combination (plus local models via Ollama).

Worried about AI code hallucinations? The Pair solves this by running two AI agents that cross-check each other:

- Mentor Agent — Plans, reviews, and validates (read-only)
- Executor Agent — Writes code and runs commands

While they work, go grab a coffee. Come back to reviewed, cross-validated…