Loading video...

Video Failed to Load

Go Home

A recent Air release added support for custom agents through Agent Client Protocol. Here’s how to configure GitHub Copilot as a custom agent in Air:

6,394,449 views • 2 months ago •via X (Twitter)

11 Comments

Jason Green's profile picture
Jason Green1 month ago

@GitHubCopilot Finally, some love for GitHub Copilot in Air. Now let's see some LSP support.

JetBrains Air's profile picture
JetBrains Air1 month ago

@GitHubCopilot It's there already :-) If you write code in Java/Kotlin, enjoy the code navigation, symbol search, and inline error highlighting.

Sebastian Buzdugan's profile picture
Sebastian Buzdugan1 month ago

@GitHubCopilot does air sandbox copilot by default, or can one bad prompt cross workspace boundaries

Axel.jsx's profile picture
Axel.jsx2 months ago

@github @GitHubCopilot Tendré que probarlo

chenyyi's profile picture
chenyyi2 months ago

@GitHubCopilot "When using the Air tool, has anyone encountered an issue where executing Bash commands doesn't inherit/use my zsh environment variables, causing it to fail to find commands like Node or Python, as well as other environment variables?"

JetBrains Air's profile picture
JetBrains Air2 months ago

@GitHubCopilot Do you execute Bash commands in the terminal or via agent? If you can share your logs and attach them here, that would help a lot: Air → Help → Diagnostic tools → Collect logs...

DiegoAlessandro's profile picture
DiegoAlessandro2 months ago

@GitHubCopilot 動き遅すぎて使い物になりませんでした。 Grokと繋げました。

Mustafa's profile picture
Mustafa1 month ago

@GitHubCopilot انا شخصيا اتمنى منيب تربح

bzrra's profile picture
bzrra1 month ago

@GitHubCopilot @getsome_air antigravity when?

Mustafa's profile picture
Mustafa1 month ago

@GitHubCopilot توة نفهمك وبن رايح رايح مكياطة حولها ملاعب سباحة ملاعب ركد بدل القهوة

Debanjan Dhar's profile picture
Debanjan Dhar2 months ago

@GitHubCopilot does not support docker and setting reasoning levels when using acp (i was using opencode)

Related Videos

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,758 views • 1 year ago