How do parallel agent sessions work?

Each agent session runs independently and can run on its own Git worktree. This isolation lets them run in parallel without affecting each other.

What are the benefits of running agents in parallel?

You can start new tasks while others are running, so you don't have to wait. Each session also keeps its own context, allowing you to switch between tasks freely without re-explaining.

What's a suggested way to get started?

Try starting two small tasks at the same time to see how they progress independently.

AI Coding AssistantsLarge Language ModelsGitHub Blog (AI)1h agoSep 4, 2026, 01:00 JST2 min read

GitHub Copilot app Runs Multiple AI Agents in Parallel

Send on LINE

Key takeaway

GitHub Copilot app now lets multiple AI agent sessions run in parallel on the same project.
Sessions work independently and don't interfere with each other.

3 Key Points

What happened
GitHub Copilot app now lets developers run multiple agent sessions at once on the same project. Each session works independently and can run on its own Git worktree, so tasks don't interfere with each other.
Why it matters
This parallel setup means you can start new tasks while others are still running. You spend time reviewing results instead of waiting for one job to finish, and each session keeps its own context so you can switch between tasks without re-explaining.
What to watch
A blog post suggests trying two small tasks at the same time as a low-stakes way to see tasks progress independently. The post describes an example with three tasks: building a funded sort feature, performing an accessibility review, and running tests.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Get news like this every morning — free

Context & Analysis

This feature addresses the bottleneck of managing multiple AI coding tasks sequentially. Previously, a developer might have to wait for one agent task to finish before starting the next, or risk them conflicting on the same code. By isolating each session on its own Git worktree, GitHub enables true parallelism.

The practical benefit is in the workflow. Instead of watching agents work, the developer's role shifts to reviewing completed results and making decisions. The user interface, with a sessions view showing the title and progress of each card, is designed to manage this concurrent workflow.

The example in the post—adding a funded sort feature, performing an accessibility review, and running tests—shows concurrent tasks of different types. The post frames the experience as less chaotic than it sounds, comparing agents to separate washing machines that run at their own settings.

FAQ

How do parallel agent sessions work?: Each agent session runs independently and can run on its own Git worktree. This isolation lets them run in parallel without affecting each other.
What are the benefits of running agents in parallel?: You can start new tasks while others are running, so you don't have to wait. Each session also keeps its own context, allowing you to switch between tasks freely without re-explaining.
What's a suggested way to get started?: Try starting two small tasks at the same time to see how they progress independently.

GitHub Blog (AI)Read Original Article

Send on LINE

Also reported by GitHub Copilot Blog

Get the latest AI Coding Assistants news every morning

For example, today's edition would include:

Meta's Muse Spark 1.3 matches GPT-5.6-Sol, claims #3 modelLatent Space · 10h ago
Meta unveils Muse Spark 1.3 with coding gainsITmedia AI＋ · 13h ago
Oracle AI Database Targets AI App DevelopmentTop Companies AI · 20h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Subscribe free →

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →