Anthropic announced a complete redesign of the Claude Code desktop app on April 14. The biggest change is support for running multiple Claude sessions side by side within the same window, along with a new sidebar to centrally manage all work sessions. This lets developers switch between different tasks quickly, just like managing browser tabs.
Multi-Session Side-by-Side
The core feature of the new desktop app is multi-session support. Developers can now open multiple Claude Code sessions in one window at the same time—for example, one session handles front-end development, another takes care of the backend API, and a third runs tests. The sidebar provides an overview of all sessions, making it easy to switch and manage them quickly.
This addresses a past pain point: with the CLI version, each terminal window can run only one Claude Code session, and parallel multitasking requires manually managing multiple terminal windows.
Integrated Development Environment Features
In addition to multi-session support, the redesign also adds several IDE-grade features:
Integrated terminal—no need to switch to an external terminal
File editor—edit code directly inside the app
HTML and PDF preview—view generated webpages or documents in real time
Faster diff viewer—quickly compare code changes
Drag-and-drop layout configuration—freely arrange the positions of each panel
All CLI plugins can be used directly in the desktop version, fully compatible with the command-line version.
A Week of Intense Claude Code Updates
The desktop redesign is the latest in a flurry of updates to Claude Code over the past week. In the last few days, Anthropic also rolled out features like Routines (scheduling / API / Webhook automation), /ultraplan for web planning, and dynamic loops. With the desktop redesign included, Claude Code is shifting from an “AI terminal tool” to a complete “AI developer workstation.”
Users can start using the new interface by downloading or updating the Claude desktop app.
This article, Claude Code desktop version undergoes a complete redesign: multi-session side-by-side, integrated terminal and file editing, moving toward an AI developer workstation, first appeared on Chain News ABMedia.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
DeepSeek V4 Pro with Ollama Cloud: One-click integration with Claude Code
According to an Ollama tweet, DeepSeek V4 Pro was released on 4/24, has been added to the Ollama catalog in cloud mode, and can call tools like Claude Code, Hermes, OpenClaw, OpenCode, Codex, etc. with just a single line of command. V4 Pro: 1.6T params, 1M context, Mixture-of-Experts; cloud inference does not download local weights. If you want to run it locally, you need to obtain the weights yourself and run it with INT4/GGUF and multi-card GPUs. Early speed tests were affected by cloud load; typical performance is about 30 tok/s, with a peak of 1.1 tok/s. It is recommended to use the cloud prototype first, and for production later, run inference yourself or use a commercial API.
ChainNewsAbmedia1h ago
Toku Launches Makimoto Open-Source AI for Asia-Pacific
Toku, a Singapore-listed customer experience software firm, launched Makimoto, an open-source conversational AI initiative for Asia-Pacific, according to the company. The first release, a transcription API, is scheduled for July 1, 2026, and will be hosted in Singapore.
Product Launch Details
Mak
CryptoFrontier2h ago
Tencent Cloud QClaw integrates with the Hermes framework, supporting switching between multiple models such as DeepSeek-V4 Pro
According to an official Tencent Cloud announcement on April 27, Tencent Cloud AI Agent desktop tool QClaw has officially released version v0.2.14. Tencent Cloud said this is the largest version upgrade QClaw has had to date. The core updates include integrating the Hermes Agent framework, upgrading the underlying model to a free-switching mode, and fully upgrading the “Inspiration Plaza” into the “Expert Plaza.”
MarketWhisper3h ago
FLOA Ecosystem Launches FloaClaw AI Suite With Multi-Scenario Skill Matrix
Gate News message, April 27 — The FLOA ecosystem has officially launched FloaClaw, its core AI toolkit, featuring a multi-scenario AI skill matrix. Access to FloaClaw's functions is limited to Agent users at level 3 and above.
FloaClaw operates on a token-based system where users purchase
GateNews3h ago
Singapore's Foreign Minister Deploys Custom AI Assistant on Raspberry Pi Using Claude Code
Gate News message, April 27 — Singapore's Foreign Minister Vivian Balakrishnan recently announced he has built a custom AI assistant system, which he calls "the diplomat's second brain," running on a Raspberry Pi 5 (a credit-card-sized microcomputer). The system integrates with his WhatsApp and
GateNews4h ago
Telegram launches a no-code AI bot tool, supporting GPT and Llama models
According to Techiexpert, on April 27 Telegram launched a no-code AI bot builder tool. Users can create and deploy AI bots through point-and-click operations without any programming skills. The new tool supports a variety of AI models such as GPT and Llama, and is integrated into Telegram Business.
MarketWhisper5h ago
