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.
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.
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
- Anthropic — “Projects redesigned: from folder to conversation” (September 17, 2026): https://claude.com/blog/projects-redesigned
- Claude Code documentation — “Claude Projects”: https://code.claude.com/docs/en/claude-projects
- Claude Help Center — “What are projects?” (September 17, 2026): https://support.claude.com/en/articles/9517075-what-are-projects
- ClaudeDevs on X — official Projects announcement (September 17, 2026): https://x.com/ClaudeDevs/status/2100633571543367691
Tools Mentioned in This Article
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.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Claude Code Projects: Parallel Sessions & Shared Context?
Related Articles
Warp adds GPT-6.1 Sol for Codex and ChatGPT subscribers
Warp’s September 29 announcement says GPT-6.1 Sol is available in Warp for use with a Codex or ChatGPT subscription.
Read more →Product UpdatesOpenAI DevDay 2026 brings Codex Cloud, code review, and Security Cloud
OpenAI’s September 2026 Codex updates add reusable cloud workspaces, automatic code review, and scheduled GitHub repository security scans.
Read more →Product UpdatesOpenAI Decisions API: Public Beta, Endpoint & Use Cases
OpenAI’s Decisions API is in public beta with GPT-6 Luna. See the /v1/decisions endpoint, text and image inputs, typed answers, and use cases.
Read more →