Product Updates

Claude Code Projects: Parallel Sessions & Shared Context

Claude Code Projects coordinate cloud threads and share repositories, instructions, and memory. Beta access is rolling out to select Pro and Max users.

By Authority AI Tools Editorial Team•2026-09-17•10 min read
Last reviewed: 2026-09-17
AATET
Authority AI Tools Editorial Team

Editorial Team

The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.

Anthropic is rolling out a redesigned Projects experience for Claude Code. In the public beta, one ongoing coordinator conversation can start and track related cloud sessions—called threads—so a longer feature, migration, or maintenance stream does not have to be managed as a collection of unrelated chats.

Claude Code logo
Claude CodeSubscription

Anthropic's terminal-based AI coding agent with Claude Opus 4.7, /ultrareview, Routines, /ultraplan, and 80.9% SWE-bench

One coordinator, many cloud threads

A Project is the coordinating conversation. Claude decides how a request should be split, starts threads for the individual tasks, and reports back as those threads finish or need direction. Each thread is a separate Claude Code cloud session with its own context and branch, so multiple pieces of work can run at the same time.

The arrangement is different from simply opening several sessions yourself: the Project keeps track of the sessions it started and gives them a shared body of work. Threads can also use their own subagents, loops, and workflows when a delegated task needs further decomposition.

Shared repositories, instructions, and memory

Project instructions provide the brief every thread starts from. Anthropic’s documentation describes using them for the target branch, checks, approval expectations, and other working rules. Threads receive the Project’s repositories, instructions, and memory, while each thread reports its result back to the coordinator.

Each cloud thread works from its own cloud copy and branch. If two threads change the same code, the overlap still has to be resolved like an ordinary merge conflict or pull request. The shared context improves coordination; it does not remove normal repository review and integration work.

Availability and limits

Projects are in public beta on Pro and Max plans and are rolling out gradually, starting with accounts that have used Claude Code cloud sessions and do not already have an existing Projects setup in Claude.ai chat or Cowork. The documentation says Team and Enterprise plans are not included yet.

Cloud threads can keep running when the user's computer is closed. When a task needs the user's machine, a thread can instead use Remote Control; that computer must stay awake and connected. Threads can be checked or steered from another device. Because a Project can run several full Claude Code sessions in parallel, it can reach usage limits faster than a single session.

Teams should treat each thread as an agent with repository access: set clear Project instructions, review the branches and pull requests it creates, and confirm which tools and credentials are available in its cloud environment.

Sources

Free Resource

2026 AI Coding Tools Comparison Chart

Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.

No spam, unsubscribe anytime.

Frequently Asked Questions

What is Claude Code Projects: Parallel Sessions & Shared Context?
Claude Code Projects coordinate cloud threads and share repositories, instructions, and memory. Beta access is rolling out to select Pro and Max users.