Copilot sdk

Skill hevangel/media-agent-skills/skills/copilot-sdk

Use GitHub Copilot SDK to programmatically call Copilot from Python. Use when integrating AI capabilities via Copilot CLI into applications.From its SKILL.md

Install

npx -y skills add hevangel/media-agent-skills --skill copilot-sdk

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.0 KB, as published. Nobody here has run it

GitHub Copilot SDK for Python

The GitHub Copilot SDK is a multi-platform SDK for integrating GitHub Copilot Agent into apps and services. It exposes the same engine behind Copilot CLI, providing a production-tested agent runtime you can invoke programmatically.

Note: This SDK is in technical preview and may change in breaking ways.

Reference

Code Snippets: scripts/
GitHub Repository: https://github.com/github/copilot-sdk
PyPI Package: https://pypi.org/project/github-copilot-sdk/

Prerequisites

GitHub Copilot Subscription: Required
Copilot CLI: Must be installed (gh extension install github/gh-copilot)
Authentication: Must be logged into GitHub CLI (gh auth login)

Installation

uv pip install github-copilot-sdk

Architecture

Your Application
       |
  SDK Client (Python)
       | JSON-RPC
  Copilot CLI (server mode)

API Reference

CopilotClient Options

Option	Type	Default	Description
`cli_path`	str	"copilot"	Path to CLI executable
`cli_url`	str	None	URL of existing CLI server
`cwd`	str	None	Working directory for CLI process
`port`	int	0	Server port (0 = random)
`use_stdio`	bool	True	Use stdio transport
`auto_start`	bool	True	Auto-start server
`auto_restart`	bool	True	Auto-restart on crash

CopilotClient Methods

Method	Description
`await client.start()`	Start the CLI server
`await client.stop()`	Stop the CLI server
`await client.create_session(config)`	Create a conversation session
`await client.resume_session(session_id)`	Resume existing session
`await client.get_models()`	Get available models

SessionConfig

Option	Type	Description
`model`	str	Model to use ("gpt-5", "claude-sonnet-4.5", etc.)
`tools`	list[Tool]	Custom tools exposed to the CLI
`streaming`	bool	Enable streaming responses
`mcp_servers`	dict	MCP server configurations

Event Types

Event Type	Description
`assistant.message`	Final assistant message
`assistant.message_delta`	Streaming message chunk
`session.idle`	Session finished processing
`tool.call`	Tool invocation
`error`	Error event

Available Free Models

gpt-5-mini

Basic Usage

import asyncio
from copilot import CopilotClient

async def main():
    client = CopilotClient()
    await client.start()
    session = await client.create_session({"model": "gpt-4.1"})
    response = await session.send_and_wait({"prompt": "What is Python?"})
    print(response.data.content)
    await session.destroy()
    await client.stop()

asyncio.run(main())