Skillget

pair-programmer

agent
SUMMARY

Pair Programmer for Claude Code, Codex and Cursor

README.md

Stargazers
Issues
Website

VideoDB

Pair Programmer

Turn your coding agent into a screen aware, voice aware, context rich collaborator.
Record your screen, microphone, and system audio in real time, then search what happened in natural language.

Works with Claude Code, Cursor, Codex, and other skill compatible agents.

Explore the docs · Report an issue · Join Discord

What is Pair Programmer?

Pair Programmer is an agentic skill that gives your AI coding assistant real time perception.

It captures:

  • Screen for visual context like terminals, editors, browser tabs, errors, and UI state
  • Microphone for your spoken intent, ideas, and debugging notes
  • System audio for tutorials, meetings, demos, and anything else your computer is playing

Once captured, that context becomes searchable.

So instead of re explaining what was on screen, copy pasting logs, or summarizing a 20 minute debugging session, you can ask:

  • What was I doing when the auth flow broke?
  • What did I say about the database migration?
  • Show me what was on screen when the test failed
  • What happened in the last 10 minutes?

This is the missing perception layer for coding agents.

Demo

https://github.com/user-attachments/assets/65af0b7e-3af9-4d05-9f0a-1415b19b4e9a

Quickstart

1. Install

If you have an older version installed, remove it first before upgrading.

npx skills add video-db/pair-programmer

2. Setup

Get a free VideoDB API key from console.videodb.io (no credit card required) and set it:

export VIDEO_DB_API_KEY=your-key

Or add it to a .env file in your project root.

Note: All commands below (starting with /) are run inside your AI coding agent — Claude Code, Cursor, Codex, etc.
The command prefix may vary by agent. For example, Codex uses $ instead of /.

Then run setup inside your agent:

/pair-programmer setup

3. Use

🎬 Record — start capturing your screen, mic, and system audio:

/pair-programmer record

A source picker will open so you can choose what to capture. Once recording starts, a lightweight overlay shows recording status, active channels, and elapsed time.

🔍 Search — query your session in natural language:

/pair-programmer search "what was I working on when I mentioned the auth bug?"

/pair-programmer search "what did I say in the last 5 minutes?"

🎤 Act — spoke an instruction into your mic? Let your agent act on it:

/pair-programmer act

📋 Summary — get a recap of recent activity:

/pair-programmer what-happened

⏹️ Stop — stop recording when you're done:

/pair-programmer stop

Why this is useful

Most coding agents can write code.

Very few can stay grounded in the same context as you.

Pair Programmer helps your agent stay on the same page by giving it access to what you saw, what you said, and what your machine was playing. That means less manual explanation, fewer broken handoffs, and a much more natural way to work.

Use it for:

  • debugging sessions
  • tutorial driven development
  • bug reproduction
  • meeting follow ups
  • architecture walkthroughs
  • voice first coding workflows

Commands

The / prefix shown below is for Claude Code. Other agents may use a different prefix (e.g. $ for Codex).

Command Description
/pair-programmer record Start recording and open the source picker
/pair-programmer stop Stop the active recording
/pair-programmer search "<query>" Search screen, mic, and audio context using natural language
/pair-programmer act Act on a spoken instruction from the mic — say what you want done, then run this
/pair-programmer what-happened Summarize recent activity
/pair-programmer setup Install dependencies and complete local setup
/pair-programmer config Update indexing and recording settings

Requirements

  • Node.js 18+
  • macOS 12+
    Windows support is currently in beta
  • VideoDB API key
    Get one at console.videodb.io

Alternative installation

You can also install via the Claude Code plugin marketplace:

/plugin marketplace add video-db/pair-programmer
/plugin install pair-programmer@videodb

Community and support

Pair Programmer is open source and designed to be adapted for your own workflows and agent use cases.

About VideoDB

VideoDB is the perception, memory, and action layer for AI agents working with video and audio.

Pair Programmer is one example of what becomes possible when agents can understand continuous media in real time.

Learn more at videodb.io

Made with ❤️ by the VideoDB team

Reviews (0)

No results found