Zed v1.27.0 - Code Editor

Zed is a high-performance code editor designed for developers who seek a fast, responsive, and modern development environment. Created by the team behind Atom and Tree-sitter, the editor is built primarily in Rust and leverages GPU acceleration to deliver a seamless editing experience.

Unlike traditional text editors, Zed integrates code editing, AI assistance, real-time collaboration, language server support, and Git tooling into a single native desktop application.

Its focus on performance makes it a compelling alternative to Visual Studio Code, particularly for developers who prefer a lightweight editor that does not rely on Electron-based architecture.

Features

High-Performance Code Editing

Zed is built around GPUI, its own GPU-accelerated user interface framework.

This architecture allows the editor to render text, interface elements, and animations efficiently. It is designed to provide responsive editing, fast navigation, and smooth interaction, even when working with large codebases.

The editor includes essential development features such as syntax highlighting, code folding, multiple selections, split panes, project navigation, and customizable keyboard shortcuts.

It also supports Vim-style editing through its built-in modal editing mode.

AI Coding Assistant

Zed includes an integrated AI assistant that helps developers understand, modify, and generate code.

Its Agent Panel provides a conversational interface where users can describe programming tasks and allow an AI agent to inspect project files, make changes, and execute supported tools.

Developers can connect different AI providers, including Anthropic, OpenAI, Google, and local model services. They can also configure their own API credentials and choose models according to their requirements.

AI assistance is not limited to chat. Zed also provides inline transformations, code generation, and editing suggestions directly within the editor.

External AI Agent Support

One of Zed's important capabilities is its support for the Agent Client Protocol (ACP).

This allows developers to use external coding agents directly inside Zed rather than relying exclusively on its built-in agent system.

Supported integrations include agents such as Claude Code, Gemini CLI, and Codex, depending on their ACP compatibility.

This makes Zed particularly useful for developers who already have preferred AI coding tools but want a unified editing environment.

Language Server Protocol Support

Zed supports the Language Server Protocol (LSP), providing intelligent programming assistance across many languages.

With the appropriate language servers installed, developers can access:

• Code completion and suggestions.

• Go-to-definition and references.

• Diagnostics and error reporting.

• Hover documentation.

• Code actions and refactoring.

• Symbol navigation.

This architecture allows Zed to support different programming languages without implementing every language-specific feature independently.

Real-Time Collaboration

Zed includes multiplayer collaboration capabilities that allow developers to work together in shared projects.

Users can invite collaborators, edit code simultaneously, follow other participants, and communicate through integrated voice and text features.

Screen sharing is also available on supported platforms.

This is useful for pair programming, code reviews, debugging sessions, and remote development teams that need to work together without constantly switching applications.

Git Integration

Zed includes built-in Git functionality for managing source code changes.

Developers can inspect modified files, review diffs, stage changes, create commits, and manage branches through the editor interface.

Its Git integration makes everyday source control operations more convenient without requiring a separate graphical Git client.

For advanced workflows, users can still access the integrated terminal and execute Git commands directly.

Integrated Terminal

Zed provides an integrated terminal that allows developers to run commands without leaving the editor.

This is useful for executing build tools, package managers, test suites, development servers, and Git operations.

Combined with project navigation and split panes, it provides a more unified development environment.

Extensions and Customization

Zed supports extensions that expand its language, theme, and development capabilities.

Users can install additional language support, syntax highlighting, themes, and other integrations through its extension system.

The editor also provides configurable settings, keymaps, themes, and project-specific configuration.

Developers can customize their environment to match their existing workflow rather than adapting entirely to the default interface.

Download Zed v1.27.0 - Code Editor - Software Mirrors
Zed v1.27.0 - Code Editor for Windows Zed-x86_64.exe | 61.75 MB zed-remote-server-windows-x86_64.zip | 34.69 MB zed-remote-server-windows-aarch64.zip | 32.95 MB Zed-aarch64.exe | 55.25 MB
Zed v1.27.0 - Code Editor for macOS Zed-x86_64.dmg | 91.92 MB zed-remote-server-macos-x86_64.gz | 35.17 MB zed-remote-server-macos-aarch64.gz | 32.33 MB Zed-aarch64.dmg | 84.08 MB
Zed v1.27.0 - Code Editor for Linux zed-remote-server-linux-x86_64.gz | 37.39 MB zed-remote-server-linux-aarch64.gz | 33.89 MB zed-linux-x86_64.tar.gz | 86.5 MB zed-linux-aarch64.tar.gz | 81.73 MB bwrap-linux-x86_64.gz | 122.8 kB bwrap-linux-aarch64.gz | 135.02 kB
Zed v1.27.0 - Code Editor Source Code Zed v1.27.0 - Code Editor Source code (zip) Zed v1.27.0 - Code Editor Source code (tar.gz)
Zed v1.27.0 - Code Editor Release Notes: This week's release includes syntax highlighting for Go 1.27 generic methods, an option to open README files by default, and AI commit messages that follow your repository's recent commit style. Features AI Improved Agent Panel memory usage by loading tool-call diffs and parsing thread message Markdown only when first viewed, instead of when loading a thread. (#65444, #65470; thanks Vanuan) Improved AI commit message generation by using the three most recent repository commit messages as style examples. (#61528; thanks matheuslrd) Improved CPU usage and disk reads while the agent was working, especially with a long thread history. (#66015) Git Added missing tooltips to the close, commit message, and "View on" buttons in the Git Graph's commit details panel. (#66016; thanks skmanoj322) Improved Git Graph rendering performance. (#66180; thanks RemcoSmitsDev) Improved the Git Panel's error message when a push was rejected because the local branch was behind the remote, explaining that remote changes must be fetched and integrated before pushing again. (#47296; thanks Aladiah96) Languages Added syntax highlighting for Go 1.27 generic methods. (#64562; thanks ndellosa95) Other Added an option to open README files by default by setting on_new_window to "readme". (#65389) Improved the Project Panel error message when moving a file or folder onto a location where one with the same name already existed. (#64344; thanks zaugust4891) Bug Fixes Fixed Solargraph completions crashing Zed in certain cases. (#66157) Fixed "Zed quit unexpectedly" appearing when quitting with cmd-q on macOS. (#66158) Fixed a crash when Tree-sitter syntax highlighting failed. (#66474) Fixed a crash when adding surrounding characters (m s) to adjacent selections in Helix mode. (#66107; thanks bugprone) Fixed a hang in Vim visual-block mode at the end of a wrapped file. (#66118) Fixed child filesystem watches losing events when a covering parent watch was removed. (#65998) Fixed collapsed inline diff hunks producing invalid word-diff highlights for multibyte UTF-8 text. (#65829; thanks Blazearth) Fixed external agents' tool call locations opening one line below the line the agent reported. (#66110) Fixed Git Graph rendering lagging behind when opening or closing the commit details panel. (#66132; thanks RemcoSmitsDev) Fixed inline review switching to a subagent's edits when the subagent started. (#66093) Fixed language server formatting requests sometimes applying incorrect changes. (#65856) Fixed language server setup failing with EBADDEVENGINES in Yarn and pnpm projects. (#65280; thanks latin-1) Fixed language servers receiving change and save notifications for files outside their dynamically registered document selectors, including unrelated files in the project. (#65253; thanks aviatesk) Fixed LLM credentials being read when disable_ai was set to true. (#66029) Fixed missed filesystem events for case-insensitive watches registered with trailing separators or equivalent path spellings. (#65995) Fixed missing Git repository, worktree, and branch names in the title bar for Windows remote projects opened in a repository subfolder. (#66142; thanks lingyaochu) Fixed missing thinking output from OpenAI-compatible Responses endpoints that emitted reasoning-text events. (#65938) Fixed on-type formatting after pressing enter being applied before the new line's indentation, which left the cursor after text inserted by language servers such as Ruby LSP. (#65769; thanks JacobNWolf) Fixed remote projects (SSH, WSL) becoming unresponsive when loading an agent thread that referred to many files outside the project. (#65189; thanks coinman-dev) Fixed renaming files, creating files, and renaming terminal tabs being cancelled when focus_follows_mouse was enabled and the mouse moved. (#66167) Fixed retryable provider failures in OpenAI-compatible chat streams not being recognized as retryable. (#66038) Fixed right-click menus and popup pickers closing when the mouse moved to another pane with focus_follows_mouse enabled. (#66173) Fixed sandboxed agent terminal commands incorrectly reporting failure under dash on Linux. (#64439; thanks NHendrickson9616) Fixed SSH connections failing when usernames containing / or \ were percent-encoded. (#64744; thanks ryanabx) Fixed status bar panel buttons doing nothing when another panel in the same dock was zoomed. (#66119; thanks ybelmach) Fixed streaming connection failures being classified as non-retryable errors for Google AI and OpenAI Responses model requests. (#65940) Fixed the automatically installed Delve debugger for Go not updating after its initial installation. (#66025) Fixed changes to focus_follows_mouse not applying to docks until Zed was restarted. (#66161) Fixed deleted files remaining in the File Finder's history. (#65660) Fixed duplicating files or folders in the Project Panel overwriting clipboard contents. (#60894; thanks shindgew) Fixed external stash renames not being reflected in the stash picker. (#55294) Fixed failed model-list fetches, such as those caused by invalid or expired API keys, being silently dropped instead of logged for Anthropic, Ollama, LM Studio, llama.cpp, OpenRouter, and Vercel AI Gateway. (#64171; thanks somtri) Fixed language servers' dynamically registered capabilities applying to files outside their document selector's pattern. (#65252; thanks aviatesk) Fixed long recent project names and the Open Project shortcut overflowing on the Welcome screen and in narrow panels. (#65531; thanks junkmailkeep) Fixed pasting in Helix select mode with shift-r, space p, or cmd-v not returning to normal mode. (#65492; thanks raum-dellamorte) Fixed project entries reappearing in Recent Projects after removal. (#66127; thanks EcutAtom336) Fixed project names in the title bar for repo.git bare clones on remote Windows hosts. (#66199; thanks lingyaochu) Fixed reordering a Markdown editor tab switching back to Markdown preview when "Open Markdown Files in Preview" was enabled. (#65795; thanks mateioprea) Fixed running Go tests on Windows failing with an invalid-directory error. (#65722; thanks giocld) Fixed scrollbar settings not applying to already open terminals, panels, and menus until they were reopened. (#66017) Fixed unnecessary-code dimming sometimes disappearing when code_lens and semantic_tokens: "full" were both enabled. (#56003) Breaking Changes and Notices Removed support for macOS Catalina and Big Sur. Zed now requires macOS 12.0 (Monterey) or later. (#65994) Removed agent checkpoints and the "Restore Checkpoint" button. Taking a checkpoint before every message made the agent slow to respond, or hang, in large Git repositories. To undo the agent's changes, reject its edits or use Git. (#65989)

Performance and Compatibility

Performance is one of Zed's main selling points.

Its native Rust architecture and GPU-accelerated interface are designed to reduce the overhead commonly associated with Electron-based editors.

Zed supports macOS, Linux, and Windows, with builds for both x86-64 and ARM64 hardware where supported.

Linux users need a Vulkan 1.3-compatible graphics driver and the required desktop portal services. Windows requires a compatible DirectX 11 graphics device and a current graphics driver.

The editor also supports Intel and Apple Silicon Macs.

Zed is actively developed, and its feature set continues to evolve. However, performance still depends on hardware, graphics drivers, language servers, extensions, and the size of the project being edited.

System Requirements

Zed supports the following environments:

• Windows: Windows 10 version 1903 or later, and Windows 11 version 22H2 or later. A 64-bit processor and DirectX 11-compatible GPU are required.

• macOS: macOS 12 or later, with Intel and Apple Silicon support.

• Linux: 64-bit x86-64 or ARM64, Vulkan 1.3-compatible graphics drivers, and required desktop portal services.

Additional requirements depend on the programming languages, language servers, extensions, and AI providers being used.

For AI features, users may need an API key, a compatible local model service, or access to an external coding agent.

Pros and Cons

Pros

• Fast native application built with Rust.

• GPU-accelerated interface.

• Integrated AI coding assistant.

• Supports multiple AI providers and external coding agents.

• Real-time multiplayer collaboration.

• Built-in Git integration.

• LSP support for intelligent code editing.

• Integrated terminal.

• Extension and customization support.

• Available on Windows, macOS, and Linux.

• Open-source under GPL-3.0-or-later, with Apache-2.0 components where specified.

Cons

• Linux requires Vulkan 1.3-compatible graphics support.

• Some AI capabilities require external API access or subscriptions.

• Language support may require separate language-server installation.

• Extension ecosystem is smaller than Visual Studio Code's.

• Not available as a supported web-based editor.

• Collaboration and some advanced features depend on network connectivity and platform support.

How to Install

Zed provides official installation packages for Windows, macOS, and Linux.

Windows

Install through Winget:

winget install -e --id ZedIndustries.Zed

macOS

Install through Homebrew:

brew install --cask zed

Linux

The official installation script supports common Linux distributions and both x86-64 and ARM64 architectures:

curl -f https://zed.dev/install.sh | sh

Alternatively, users can download platform-specific packages from the official website.

For developers interested in building Zed from source, the project provides platform-specific compilation instructions in its GitHub repository.

Final Verdict

Zed is an impressive code editor that combines performance, modern development tools, AI assistance, and collaboration in one application.

Its biggest advantage is its native architecture. Built with Rust and GPU acceleration, it provides a different approach to code editing compared with traditional Electron-based editors.

The integrated AI assistant and Agent Client Protocol support are also valuable additions. Developers can work with multiple AI coding tools without leaving their primary development environment.

However, its extension ecosystem is still developing, and some platform requirements, particularly Vulkan support on Linux, may limit compatibility with older hardware.

Overall, Zed is an excellent choice for developers looking for a fast, modern, and open-source code editor with built-in AI capabilities. It is especially attractive to users who want an alternative to Visual Studio Code without sacrificing essential development features.

Sources

• Zed GitHub Repository

• Official Zed Website

• Installation Guide and System Requirements

• Zed AI Documentation

• Zed Agent Client Protocol

• Zed Licensing Information

Free

Download

Software Informations:
Developer:
Zed Industries
Operating System:
Windows / macOS / Linux
Date Added:
2026-11-08T07:11:40.000Z

DiskRaptor v1.0.53

DiskRaptor is a modern open source disk space analyzer designed to help you quickly understand what is consuming storage on your computer. Built with Rust and Tauri 2, it is positioned as a faster, more modern alternative to tools such as WinDirStat and DaisyDisk.

What makes DiskRaptor particularly interesting is its focus on handling very large file systems. The project uses native Rust scanning components and a virtual tree interface designed to remain responsive even when working with millions of files.

What Is DiskRaptor?

DiskRaptor is a cross platform disk usage analyzer for Windows, macOS, and Linux.

Its main purpose is simple. You select a drive or directory, let DiskRaptor scan it, and then explore which folders and files are consuming the most space.

The project is built with Rust and Tauri 2. The native scanning engine handles file system traversal while the interface runs inside the operating system's native webview. This keeps the application relatively lightweight compared with applications that bundle an entire Chromium runtime.

Fast Disk Scanning

Performance is one of DiskRaptor's main selling points.

The project uses a parallel scanning engine on macOS and a reliable walkdir-based engine on Windows and Linux. It is designed to handle drives containing millions of files, with the project documenting support for scans involving up to 20 million nodes.

Access denied folders are handled gracefully as well. Instead of completely stopping a scan because it encounters a protected directory, DiskRaptor logs the problem and continues scanning.

For users with large SSDs, hard drives, external drives, or development machines containing huge numbers of files, this approach can make a significant difference.

Virtual Tree View

DiskRaptor uses a virtual tree interface that renders only the items currently visible on screen.

This is important when working with extremely large directory structures. Loading millions of files into a conventional browser interface would quickly become impractical.

The project claims that its virtual tree can handle more than 10 million files while remaining responsive.

You can navigate through folders, inspect file sizes, and identify which directories are responsible for consuming storage.

Multiple Visualization Options

DiskRaptor doesn't rely on a single visualization.

It provides several ways to understand disk usage, including:

• Pie charts

• Squarified treemaps

• Bar charts

• Galaxy 3D visualization

The application also provides a Top 50 list of the largest files. Selecting an item in the visualization can take you directly to the corresponding location in the directory tree.

The treemap is particularly useful when you want a quick visual overview of a large drive.

Find Large Files

Finding large files is one of the most practical reasons to use a disk analyzer.

DiskRaptor highlights the largest files and allows you to inspect their location directly.

This can quickly reveal things such as old installers, virtual machine images, Docker data, video files, build artifacts, backups, and other files that have quietly consumed hundreds of gigabytes.

Duplicate File Detection

DiskRaptor also includes duplicate detection.

It uses content hashing with xxHash3 to identify files that contain the same data.

This is more useful than simply comparing filenames because files with different names can still contain identical content.

Duplicate detection can be particularly helpful for large collections of photographs, videos, archives, downloads, and project backups.

Empty Folder Finder

The application can identify empty directories and allow you to jump directly to them.

This is a relatively small feature, but it can be useful when cleaning up development directories, extracted archives, or old project structures.

File Search and Filtering

DiskRaptor provides search functionality for scanned results.

You can search by filename pattern and filter results by file type, including:

• Images

• Video

• Audio

• Archives

• PDF files

This makes it easier to locate specific categories of files without manually navigating the entire directory tree.

File Management

DiskRaptor isn't purely a visualization tool.

Its context menus provide actions such as opening a file in Explorer or Finder, opening a terminal, viewing properties, copying a path, moving an item to the trash, and scanning a particular folder.

The ability to move files to the trash directly from the application makes cleanup considerably more convenient.

Because file deletion is potentially destructive, users should still verify what they are removing before performing cleanup operations.

Trash Recovery

Another useful feature is trash management.

DiskRaptor can browse items in the operating system's trash, restore them, or permanently delete them.

This gives the application some basic recovery functionality rather than treating deletion as a one way operation.

Reports and Export

DiskRaptor can export disk analysis results in several formats.

Supported options include:

• HTML reports

• CSV

• JSON

The HTML report can be shared as a standalone report containing statistics and charts. CSV and JSON exports are useful when you want to process the results with another application or script.

This is particularly useful for administrators who need to document storage usage rather than simply inspect it interactively.

Cross Platform Support

DiskRaptor supports:

• Windows

• macOS

• Linux

The project provides a Windows NSIS installer, a universal macOS binary supporting both Intel and Apple Silicon, and a DEB package for Debian and Ubuntu.

This makes it considerably more versatile than Windows-only disk analyzers.

Interface and Customization

The interface supports both dark and light modes, with the selected setting saved for future sessions.

It also supports 25 languages with automatic language detection and a language switcher.

Drag and drop is supported as well, allowing folders to be dragged from Explorer or Finder into DiskRaptor for scanning.

The interface also has resizable panels, keyboard navigation, and contextual menus.

Technology

DiskRaptor is built around Rust and Tauri 2.

The architecture separates the native layer from the interface. Rust handles scanning and native operations while JavaScript handles the user interface through the operating system's webview.

That means DiskRaptor does not need to ship its own Chromium browser engine.

On Windows it uses WebView2, macOS uses WKWebView, and Linux uses WebKitGTK.

For a disk utility that needs to remain responsive while processing very large directory trees, this is a sensible architecture.

Download DiskRaptor v1.0.53 - Software Mirrors
DiskRaptor v1.0.53 for Windows DiskRaptor.exe | 14.27 MB DiskRaptor-windows-x64.msix | 5.35 MB DiskRaptor-1.0.53-windows-x64.msi | 8.07 MB DiskRaptor-1.0.53-windows-x64.exe | 5.98 MB DiskRaptor-1.0.53-windows-x64-silent.msi | 5.37 MB DiskRaptor-1.0.53-windows-x64-silent.exe | 3.86 MB
DiskRaptor v1.0.53 for macOS DiskRaptor-1.0.53-macos-universal.pkg | 13.89 MB DiskRaptor-1.0.53-macos-universal.dmg | 14.78 MB
DiskRaptor v1.0.53 for Linux DiskRaptor-1.0.53-linux-x86_64.rpm | 7.54 MB DiskRaptor-1.0.53-linux-x86_64.deb | 7.54 MB DiskRaptor-1.0.53-linux-x86_64.bin | 11.28 MB DiskRaptor-1.0.53-linux-x86_64.AppImage | 82.37 MB
DiskRaptor v1.0.53 Source Code DiskRaptor v1.0.53 Source code (zip) DiskRaptor v1.0.53 Source code (tar.gz)
DiskRaptor v1.0.53 Release Notes: Full Changelog: v1.0.52...v1.0.53

Pros

• Open source

• Free to use

• Windows, macOS, and Linux support

• Built with Rust

• Tauri 2 architecture

• Fast directory scanning

• Designed for millions of files

• Virtual tree view

• Treemap visualization

• Pie charts

• Bar charts

• Galaxy 3D view

• Top 50 largest files

• Duplicate file detection

• Empty folder detection

• Filename search

• File type filtering

• Trash recovery

• Direct file management

• HTML report export

• CSV export

• JSON export

• Dark and light modes

• 25 languages

• Drag and drop support

• Apple Silicon support

Cons

• The project is still relatively young

• Some advanced features may need further refinement

• Scanning very large drives can still consume substantial CPU and storage I/O

• Deleting files directly from a disk analyzer requires caution

• The visualization features may be more than users need for simple disk cleanup

• Linux packaging currently focuses on DEB distributions

DiskRaptor vs WinDirStat

WinDirStat remains one of the best known Windows disk usage analyzers, but DiskRaptor takes a more modern approach.

DiskRaptor is cross platform, built with Rust and Tauri, supports multiple visualization modes, includes duplicate detection and trash recovery, and is designed around very large directory trees.

WinDirStat has the advantage of being a mature and well established Windows application.

For users who want a modern cross platform alternative, DiskRaptor is much more interesting.

DiskRaptor vs DaisyDisk

DaisyDisk is known for its polished macOS interface and strong visualization capabilities.

DiskRaptor brings a similar visual approach to Windows and Linux while also supporting macOS.

Its open source nature is another major difference.

For someone who wants a free and open source disk analyzer that works across multiple operating systems, DiskRaptor is a compelling alternative.

Who Should Use DiskRaptor?

DiskRaptor is a good choice for anyone who regularly needs to answer the question, "What is using all my disk space?"

It is especially useful for:

• Developers

• System administrators

• Power users

• NAS and storage users

• Large media collections

• Users managing external drives

• People cleaning old project files

• Anyone with a rapidly filling SSD

The large file and duplicate detection features are particularly useful for development machines where build artifacts, package caches, Docker files, virtual machines, and old repositories can accumulate surprisingly quickly.

Final Verdict

DiskRaptor is an impressive open source disk space analyzer with a clear focus on performance and usability.

Its Rust based scanning engine, virtual tree interface, multiple visualizations, duplicate detection, file filtering, and report export make it much more than a basic folder size viewer.

The cross platform support is another major advantage. You can use the same general workflow on Windows, macOS, and Linux rather than maintaining different disk analysis tools for each operating system.

The project is also under active development. The GitHub repository currently shows more than 800 commits, six open pull requests, and recent updates in August 2026.

It is still less mature than long established applications such as WinDirStat, so some users may encounter rough edges. Nevertheless, the architecture and feature set make DiskRaptor one of the more interesting modern alternatives in this category.

If you want a fast, open source, cross platform disk space analyzer, DiskRaptor is well worth trying.

Free

Download

Software Informations:
Developer:
DiskRaptor
Operating System:
Windows / Linux / macOS
Date Added:
2026-11-08T06:22:38.434Z

OpenBot v0.65.0

OpenBot is a desktop workspace for managing persistent AI agents from a single interface. Instead of switching between separate coding assistants and conversations, users can assign different agents their own workspaces, queue tasks, exchange files, and collaborate on projects.

The application supports several AI coding tools, including OpenAI Codex, Claude Code, Gemini, Grok, OpenCode, Cursor, and Cline. It also offers an embedded browser, agent-to-agent messaging, and remote access from mobile devices. OpenBot is designed primarily for developers and power users who want to coordinate multiple AI assistants while keeping their working files and conversations on their own computer.

Although the source code is publicly available on GitHub, the licensing distinction is important: current releases use the PolyForm Noncommercial License, so commercial use requires separate permission. Older releases up to and including 0.1.11 remain under Apache 2.0.

Features

Multiple AI Agents

OpenBot lets users create persistent agents with individual instructions, workspaces, conversations, and model settings. Supported providers include Codex, Claude Code, Grok, OpenCode, Gemini, Cursor, and Cline, with custom agents and compatible model endpoints also supported.

Each agent can maintain its own working context, making it easier to separate tasks such as writing code, investigating bugs, reviewing changes, and researching documentation.

Persistent Workspaces and Task Queues

Each agent receives a dedicated workspace for its files and ongoing work. Users can send tasks to an agent while it is busy, with messages waiting in a queue until the agent is ready.

Queue controls include pausing, resuming, cancelling, and recovering queued work after a crash. Context monitoring and automatic compaction also help agents manage longer conversations without exhausting their model context window.

Agent-to-Agent Collaboration

OpenBot supports communication between agents, including messages, replies, reactions, and file transfers. Shared desktop channels can organize collaborative tasks around a designated task owner, with options to delegate work and manage the task's progress.

This approach is useful for workflows that benefit from multiple perspectives, such as having one agent implement a feature while another reviews the result. However, dividing work among several agents does not automatically guarantee better output. Results still depend on the models, instructions, and task design.

Embedded Browser and Computer Use

The built-in browser allows agents to open, inspect, and interact with web pages. Optional Computer Use support can provide mouse, keyboard, and screen interaction on supported desktop platforms.

These capabilities extend OpenBot beyond code generation. Agents can assist with browser-based research, repetitive computer tasks, and workflows involving web interfaces.

Computer interaction also introduces additional risks. An agent that can operate a browser may encounter malicious instructions on web pages or interact with services in unintended ways.

Custom Models and Providers

OpenBot supports custom OpenAI-compatible endpoints and custom agents through the Agent Client Protocol. It can detect supported local model servers, including Ollama and LM Studio, and work with compatible providers.

This flexibility is useful for users who want to experiment with different models or integrate existing AI tools rather than commit to a single provider.

However, local model support does not make the entire application automatically offline. Cloud-based providers still receive the prompts sent to them, and browsing or connected services require network access.

File Sharing and Attachments

Agents can exchange managed files and share attachments through conversations. The application supports common document and project workflows, with support for audio, video, and ZIP attachments under documented file and message limits.

Agents can use their available tools to inspect supplied files, but OpenBot does not itself automatically transcribe every audio recording or decode every video attachment.

Mobile and Remote Access

OpenBot provides ways to connect to a running computer from supported mobile clients. This allows users to check conversations and interact with their agents without remaining at their desktop.

Remote access depends on the host and connection configuration. Some agents, particularly those tied to local command-line tools, continue to run on the computer where they were started rather than being transferred to the mobile device.

Local-First Data Storage

OpenBot is designed to keep workspaces, conversations, attachments, and browser data on the computer running the application. Cloud services support account and remote-access functionality, while AI providers receive the prompts sent to their models.

This separation gives users more control over local project data, but it is not equivalent to complete privacy or offline operation. Users should review the application's privacy documentation and each provider's data policies before using confidential material.

Download OpenBot v0.65.0 - Software Mirrors
OpenBot v0.65.0 for Windows OpenBot-0.65.0-x64.exe | 221.91 MB
OpenBot v0.65.0 for macOS OpenBot-0.65.0-x64.zip | 259.3 MB OpenBot-0.65.0-x64.dmg | 268.66 MB OpenBot-0.65.0-arm64.zip | 251.11 MB OpenBot-0.65.0-arm64.dmg | 260.33 MB
OpenBot v0.65.0 for Linux OpenBot-0.65.0-x86_64.AppImage | 235.43 MB OpenBot-0.65.0-arm64.AppImage | 177.42 MB
Others Download related to OpenBot v0.65.0 OpenBot-Host-0.65.0-arm64.pkg | 50.02 MB
OpenBot v0.65.0 Source Code OpenBot v0.65.0 Source code (zip) OpenBot v0.65.0 Source code (tar.gz)
OpenBot v0.65.0 Release Notes: What's Changed Let users choose the spoken replies model: Supertonic, ElevenLabs or xAI by @NorbertBodziony in #5555 Show which workflow branch has no answer at a model join by @NorbertBodziony in #5561 Start dev builds with the Dynamic Island and agent dock off by @NorbertBodziony in #5562 Add a setting to turn off the hold to quit on a Mac by @NorbertBodziony in #5566 Use API credit for Claude agents on an Anthropic API key by @NorbertBodziony in #5571 Open an agent page in the side panel and quote text from it by @NorbertBodziony in #5570 Let users choose a chat background for Light and for Dark by @NorbertBodziony in #5577 Give notifications a new look by @NorbertBodziony in #5576 Make the chat send and the message box move as Grok Bot does by @NorbertBodziony in #5578 Add "Delete history" to the agent and channel settings by @NorbertBodziony in #5579 Add Mistral as a built-in provider through Mistral Vibe by @NorbertBodziony in #5582 Show the selected sidebar row with a grey fill in the light theme by @NorbertBodziony in #5585 Use one registry for side panel panes by @NorbertBodziony in #5587 Open channel file links to files outside the agent workspace by @NorbertBodziony in #5588 Add Groq Whisper as dictation models by @NorbertBodziony in #5586 Put the Workspace only sandbox in the Claude settings file by @Sniezka1927 in #5597 Make the agent browser use fewer turns by @NorbertBodziony in #5589 Register MCP sign-in again with localhost when 127.0.0.1 is refused by @Sniezka1927 in #5599 Let Codex live voice work with agents on joined servers by @NorbertBodziony in #5592 Keep agent browser pages drawn while the macOS window is minimized or hidden by @Sniezka1927 in #5604 Scroll the agent dock when it has too many agents by @NorbertBodziony in #5605 Add a Library page to the window rail by @NorbertBodziony in #5606 Hide the agent dock from window switchers on macOS by @NorbertBodziony in #5607 Keep the AppImage updater beside a self-hosted server by @Absterrg0 in #4341 Make the triage skill rate UX impact for casual users by @NorbertBodziony in #5608 Connect the host to Signal again when its socket does not answer by @NorbertBodziony in #5611 Run the OpenCode canary case on a fake model on loopback by @NorbertBodziony in #5609 Complete Gemini turns that end silently after output or optional reply by @matheustx017 in #5596 fix(pi): send developer instructions to the Pi CLI in a file by @huajar in #3777 Ship Noto CJK fonts in the Docker image so the embedded browser renders CJK text by @sarequl in #4442 Show a white root on the agent display of a server by @NorbertBodziony in #5613 Send memories and section-mates with the turns for ACP, Muse and Pi by @NorbertBodziony in #5573 Keep the named browser profile when an agent is duplicated by @NorbertBodziony in #5619 Turn off Claude Code features that OpenBot agents cannot use by @NorbertBodziony in #5616 fix(routines): let a routine run list routines (#4406) by @sarequl in #4542 Keep the reported cost and the token counts of a custom agent in usage by @NorbertBodziony in #5620 Stop the Local scripts settings page from locking the window by @Sniezka1927 in #5621 Reconnect remote servers soon after the network returns by @NorbertBodziony in #5622 Resume routines when the wake event never arrives by @NorbertBodziony in #5623 Fail the Gemini turn when Google asks to verify the account by @NorbertBodziony in #5625 Send fewer prompt tokens in each Pi agent request by @NorbertBodziony in #5629 Send fewer prompt tokens in each OpenCode agent request by @NorbertBodziony in #5632 Make Grok agent requests smaller by @NorbertBodziony in #5634 Show the error of a failed tool step in the turn steps by @NorbertBodziony in #5635 Add an Inception Labs key for dev harness tests by @NorbertBodziony in #5636 Reduce the Hermes prompt tokens in each request by @NorbertBodziony in #5638 Make the compact sidebar list fade longer at its edges by @NorbertBodziony in #5639 Correct the text of the steer setting by @NorbertBodziony in #5626 Keep agent progress updates in a channel by @NorbertBodziony in #5624 Read progress updates aloud in a voice conversation by @NorbertBodziony in #5628 Add Send now for queued messages of agents that cannot steer by @NorbertBodziony in #5633 Send fewer tool and prompt tokens in each Claude and Codex request by @NorbertBodziony in #5642 Send fewer repeated memory and turn context tokens by @NorbertBodziony in #5645 Send fewer tokens in background model calls by @NorbertBodziony in #5649 Send Codex memories and section teammates with the turns by @NorbertBodziony in #5647 Send smaller browser and GitHub tool results to agents by @NorbertBodziony in #5652 Continue an agent turn that ends on more next-step phrases by @Sniezka1927 in #5656 Send fewer prompt tokens to Codex, and add web search for agents with no search of their own by @NorbertBodziony in #5658 Stop island and agent dock motion while the user is in other apps by @NorbertBodziony in #5664 Show one Attach files item in the message box menu by @Sniezka1927 in #5655 Open Shared/… file chips from the shared folder by @Sniezka1927 in #5659 Fill saved logins in text fields that the page masks as passwords by @Sniezka1927 in #5669 Keep a browser tab open when its first page does not load by @Sniezka1927 in #5670 Move Cursor agents to their backup model when the plan is used up by @Sniezka1927 in #5671 Use less memory in tabs, provider processes and app windows by @NorbertBodziony in #5672 Show agent dock replies while the OpenBot window is hidden by @Sniezka1927 in #5687 Tell agents about saved logins that arrive after their chat started by @NorbertBodziony in #5694 Prepare the v0.65.0 release by @NorbertBodziony in #5696 New Contributors @Absterrg0 made their first contribution in #4341 @matheustx017 made their first contribution in #5596 @huajar made their first contribution in #3777 Full Changelog: v0.64.0...v0.65.0

Performance and Compatibility

OpenBot supports macOS 13 or newer on Apple silicon and Intel processors, Windows 10 or newer on x64 systems, and Linux on x64 or ARM64 through AppImage packages.

The application brings multiple AI tools into one desktop interface, potentially reducing the need to switch between separate applications. Persistent workspaces, queued messages, and agent collaboration are particularly useful for longer development projects.

Actual performance depends heavily on the selected AI provider, model, hardware, network connection, and number of active agents. Running several agents can increase API usage, consume additional system resources, and produce more output to review.

OpenBot is a development preview, so users should expect ongoing changes and possible limitations. It is better suited to experimentation and workflows that can tolerate occasional problems than to environments requiring strict operational guarantees.

Important security consideration: The project's documentation warns that agents currently run with full access to their permitted execution environment and an approval policy that does not require confirmation for every action. After the initial consent, agents may read or modify files, execute commands, access the network, and control the embedded browser without additional per-action approval. Use agents and tasks you trust, maintain backups, and carefully review the security documentation before granting access to important files or production systems.

System Requirements

OpenBot's published platform requirements are:

• macOS: Version 13 or newer, supporting Apple silicon and Intel Macs.

• Windows: Version 10 or newer on x64 systems.

• Linux: x64 or ARM64 using the AppImage distribution.

Additional requirements depend on the AI providers and integrations selected. Some agents need their own command-line tools, authentication, subscriptions, or API credentials. Local model servers also require compatible models and sufficient hardware resources.

For Linux users, certain environments may require additional configuration. The documentation identifies AppArmor-related restrictions on Ubuntu 23.10 or newer and Debian 13, while remote desktop functionality has specific display-server and architecture limitations.

Pros and Cons

Pros

• Manages multiple AI coding agents in one desktop application.

• Provides separate workspaces and persistent conversations for individual agents.

• Supports task queues, delegation, and agent-to-agent communication.

• Includes an embedded browser and optional computer interaction.

• Supports multiple AI providers and compatible custom endpoints.

• Offers file sharing, attachments, and remote access from mobile clients.

• Designed to keep workspaces and conversations on the host computer.

• Provides Linux packages alongside Windows and macOS releases.

Cons

• Development-preview status means features and behavior may change.

• Agents currently have broad execution access without per-action approval.

• Cloud-based providers still receive prompts and require network access.

• Multiple agents can increase model usage, resource consumption, and review overhead.

• Some providers require separate authentication, subscriptions, or API credentials.

• Current licensing restricts commercial use without separate permission.

• Linux users may need additional configuration for certain environments and features.

How to Install

1. Visit the official OpenBot website.

2. Open the download section and select the package for your operating system.

3. Install the application using the downloaded package.

4. Launch OpenBot and follow the onboarding instructions.

5. Connect a supported AI provider or configure a compatible model endpoint.

6. Create an agent, configure its instructions, and select its model and workspace.

7. Test the agent with a low-risk task before granting access to important files or workflows.

8. Review the security settings and project documentation before enabling browser control, computer interaction, or tasks involving sensitive information.

Linux users should follow the official installation instructions for their distribution, especially if AppArmor restrictions prevent the application from launching. For safety, obtain release packages from the project's official distribution channels and verify available checksums or build attestations.

Final Verdict

OpenBot is an interesting workspace for developers who want to coordinate several AI agents instead of managing each assistant separately. Its persistent workspaces, task queues, agent collaboration, browser integration, and support for different providers make it useful for experimenting with more advanced AI-assisted workflows.

Its local-first design is another advantage for users who prefer to keep project files and conversation history on their own computers. Nevertheless, local storage does not prevent cloud-based AI providers from receiving prompts, and the application's current full-access execution model deserves careful attention.

The development-preview status and noncommercial licensing are also important considerations. Users should distinguish between publicly available source code and software licensed for unrestricted commercial use.

OpenBot is worth exploring for developers and AI enthusiasts who want a flexible, multi-agent workspace. Its feature set is promising, but the security model, preview status, and current licensing restrictions make it less suitable for sensitive production workflows or commercial deployment without further evaluation.

Free

Download

Software Informations:
Developer:
nightly-labs
Operating System:
Windows / macOS / Linux
Date Added:
2026-11-08T06:22:10.288Z

Aiarty Image Matting V2.7 for Mac (Lifetime) - Discount 20% OFF

Aiarty Image Matting is an advanced AI powered tool designed to separate subjects from backgrounds with high accuracy. The software uses deep learning models to detect edges, hair details, transparency, and complex shapes, making background removal fast and precise. It is ideal for photographers, designers, content creators, and businesses that need clean cutout images for marketing, ecommerce, and creative projects.

Get Discount 20% OFF using "SWMR" Coupon code for the Aiarty Products below:
Aiarty Image Enhancer (Standard - 3PCs) Aiarty Image Enhancer (Lifetime - 3PCs) Aiarty Image Matting (Lifetime - 3 PCs) Aiarty Image Matting (Standard - 3 PCs) Aiarty Image Matting (Commercial license) Aiarty Image Tool Bundle (Lifetime) Aiarty Video Enhancer (Lifetime- 3 PCs) Aiarty Video Enhancer (Standard - 1 PC) Aiarty 3-in-1 Bundle (Lifetime) Aiarty Media Enhancer Bundle (Lifetime)	AIarty Image Enhancer for Mac (Standard) Aiarty Image Enhancer for Mac (Lifetime) Aiarty Image Matting for Mac (Lifetime) Aiarty Image Matting for Mac (Standard - 3 Macs) Aiarty Image Matting for Mac (Commercial license) Aiarty Image Tool Bundle for Mac (Lifetime) Aiarty Video Enhancer for Mac (Lifetime) Aiarty Video Enhancer for Mac (Standard) Aiarty 3-in-1 Bundle for Mac (Lifetime) Aiarty Media Enhancer Bundle for Mac (Lifetime)
Aiarty Image Tool Bundle (Lifetime) - Discount 50% Off

What Is Aiarty Image Matting

Aiarty Image Matting is a smart image processing solution that performs automatic background separation. It analyzes an image, identifies the subject, and produces a high quality cutout with clean edges. The tool works on portraits, products, animals, and various complex objects. The AI model is trained to handle challenging scenarios such as fine hair strands, uneven lighting, and semi transparent materials.

Aiarty Image Matting helps users produce studio quality results without needing manual masking or advanced editing skills. This reduces production time and ensures consistent quality for large batches of images.

Key Features of Aiarty Image Matting

High Precision Background Removal

Aiarty Image Matting delivers accurate cutouts by analyzing pixel level details. It preserves fine edges and natural outlines, making the subject look realistic after removal.

Support for Complex Objects

The software handles hair, fur, transparent materials, and detailed textures. This makes it suitable for fashion photos, product shots, and creative artwork.

Fast AI Processing

Aiarty Image Matting provides quick results even for high resolution images. The AI engine is optimized for speed while maintaining precision.

Batch Processing

Users can upload multiple images and process them all at once. This is valuable for ecommerce stores and graphic designers who need to edit large image collections.

Background Replacement

After removing the background, users can replace it with a solid color, gradient, or custom image. This is ideal for marketing materials, product catalogs, and promotional designs.

Simple Interface

The tool is designed to be user friendly even for beginners. Most tasks require only a few clicks and do not demand professional editing skills.

High Resolution Output

Aiarty Image Matting produces sharp and clean results that remain suitable for printing, digital ads, and high quality media.

Cloud Based Convenience

Images are processed online, so there is no need for high end hardware. Users can access the tool from any device with a modern browser.

Benefits of Aiarty Image Matting

Saves Significant Editing Time

Manual background removal is slow and tedious. Aiarty Image Matting automates the process and delivers instant results.

Ideal for Ecommerce

Product photos require clean white or transparent backgrounds. This tool produces consistent outputs for stores, catalogs, and product listings.

Perfect for Creative Projects

Designers can isolate subjects quickly and focus on composition rather than manual cutouts.

Improves Content Quality

High precision matting results in cleaner, sharper visuals that enhance branding and marketing materials.

No Special Skills Needed

Even users with limited editing experience can generate professional results.

Conclusion

Aiarty Image Matting is a powerful AI powered background removal tool that offers impressive precision and speed. Its ability to handle complex edges, support batch processing, and deliver high resolution results makes it valuable for photographers, ecommerce stores, designers, and marketing teams. For anyone needing fast and accurate image cutouts without advanced editing work, Aiarty Image Matting stands out as a dependable and efficient solution.

$87.2$109

Buy Now

Download

Software Informations:
Developer:
Digiarty Software
Operating System:
Mac
Date Added:
2026-11-08T06:07:28.166Z

NewPipe v0.29.2

NewPipe is a free and open-source Android application for watching and listening to content from YouTube and other supported media services. It provides a lightweight alternative to official client applications and does not require Google Play Services or an account to browse supported services.

The application can play video at resolutions up to 4K, provide background audio playback, download media, manage subscriptions and playlists, and play content through a floating popup player.

Features

NewPipe supports several video and audio services, including YouTube, YouTube Music, PeerTube, Bandcamp, SoundCloud, and media.ccc.de. YouTube is currently the best-supported service according to the project.

Key features include:

• Video playback up to 4K

• Background audio playback

• Popup player

• Live stream support

• Subtitle and closed-caption support

• Video and audio search

• Channel search

• Playlist search

• Channel subscriptions without an account

• Subscription notifications

• Channel groups

• Local playlists

• Watch history

• Video and audio downloads

• Subtitle downloads

• Queue management

• Kodi integration

• Comments

• Related-video controls

• Support for age-restricted content

• Multiple audio and subtitle options

NewPipe's subscription system is local rather than tied to an online account. This allows users to subscribe to channels without signing into YouTube.

The application also avoids proprietary libraries such as Google Play Services. This makes it suitable for Android devices and custom ROMs that do not include Google's services.

Download NewPipe v0.29.2 - Software Mirrors
NewPipe v0.29.2 for Android NewPipe_v0.29.2.apk | 16.19 MB
NewPipe v0.29.2 Source Code NewPipe v0.29.2 Source code (zip) NewPipe v0.29.2 Source code (tar.gz)
NewPipe v0.29.2 Release Notes: This releases brings a bunch of player fixes and improvements for YouTube. New [YouTube] Add support for "Podcasts" and "Courses" tabs - #13713 Add brotli support to downloader - #13789 Feature: Divide player seekbar by chapters - #13430 Improved Improve look of search menu "titles" - #13605 [YouTube] Update Piped and Invidious instances - #13767 Enabled asynchronous ARM Memory Tagging Extension (MTE) - #13862 Show full subtitle names when the service exposes them - #13874 a11y: contentDescription for play button and sort icon - #13851 Show queue progress and total duration for popup and background queue #13942 #13972 Translation updates strings #13707 #13737 #13748 #13791 #13832 #13885 compose #13708 #13736 #13750 #13788 #13839 #13889 Fixed Fix audio ducking issue by using ExoPlayer's automatic audio focus management - #13169 Fix: blacklist JMGO N1S 4K and TCL 65Q651G for media tunneling - #13756 Fix: black video delay when entering fullscreen - #13764 Fix opening links with timestamps - #13781 Fix playlist not clearing when navigating back - #13732 Use app locale instead of content locale for local list dates - #13843 Hide current fragment when opening settings search - #13857 Keep the chosen audio track when resuming downloads - #13883 Feed: prevent group name subtitle leak into other fragments - #13974 [Bandcamp] Fix NetworkOnMainThreadException on rotate / back - #13955 Development Replace KeyboardUtil with library helper class - #13711 Mention word mark in README - #13685 Handle Description conversion to record class - #13553 Update PR template to encourage users to explain their testing/QA procedure - #13720 Make using the PR template mandatory in the contribution guidelines - #13804 [YouTube] Update NewPipeExtractor and adapt to removals - #13801 Migrate settings appearance screen - #13684 fix: log stream progress save errors with Log.e - #13849#13849 Add missing function parameter comment documentation - #13865 Fix inconsistent History page title when opening the History page from the sidebar - #13457 Update user agent to Firefox ESR 153 - #13887 Dependency updates Update Gradle and dependencies - #13787 #13901 #13935 #13988 Migrate room to v3 - #13903

Performance and Compatibility

NewPipe is designed as a lightweight Android streaming client. It retrieves information through official APIs where available and uses website parsing or internal APIs when an official service API is unavailable or unsuitable.

One important limitation is that services such as YouTube can change their website and internal interfaces. Because NewPipe depends on extracting information from these services, changes can temporarily break individual features. The project's release history shows fixes for YouTube playback, channel parsing, downloads, playlists, and other service-specific issues.

NewPipe is currently distributed outside Google Play. The project recommends its own F-Droid repository for most users, while APKs are also available through GitHub Releases. The project specifically warns that publishing NewPipe or its forks on Google Play violates Google's terms.

The project describes the application as being in beta, so occasional bugs can occur.

System Requirements

NewPipe is designed for Android devices.

The current release line requires Android 6.0 or newer. Android 5 support was dropped in a recent release.

No Google account or Google Play Services installation is required.

NewPipe can therefore run on compatible Android devices without Google's proprietary mobile services.

Pros and Cons

Pros

• Free and open source

• Lightweight

• No Google Play Services required

• No account required for normal use

• YouTube and YouTube Music support

• PeerTube support

• Bandcamp support

• SoundCloud support

• Background playback

• Popup player

• Video and audio downloads

• Subtitle downloads

• Local subscriptions

• Local playlists

• 4K playback

• Live streams

• Channel groups

• Privacy-focused design

• GPL-3.0 licensed

Cons

• Android only

• Not available through Google Play

• Service changes can temporarily break features

• YouTube is dependent on website parsing and internal APIs

• Project is still described as beta

• Some supported services have less functionality than YouTube

• No official account synchronization with YouTube

How to Install

The NewPipe project recommends adding its custom repository to F-Droid and installing the application from there. Users can also download the APK directly from the project's GitHub Releases page.

For the F-Droid method:

1. Add the official NewPipe repository to F-Droid.

2. Search for NewPipe.

3. Install the application.

4. Allow the requested permissions.

5. Open NewPipe and configure your subscriptions and playback preferences.

Alternatively, download the appropriate APK from GitHub Releases and install it manually. The project recommends comparing the APK signing key when using this method.

Subscriptions and other local data can also be backed up and restored through NewPipe's settings.

Final Verdict

NewPipe remains a focused alternative to official Android media applications, particularly for users who want background playback, downloads, local subscriptions, and playback without Google Play Services.

Its privacy-oriented architecture is one of its defining characteristics. The application does not require an account for normal use, does not depend on proprietary Google libraries, and keeps subscriptions and other local functionality on the device.

The main limitation is its dependence on external services. YouTube and other platforms can change their interfaces or access mechanisms, which can temporarily affect playback or other features. The project's active development and regular fixes help address these compatibility problems.

For Android users looking for a lightweight, open-source media client with background playback, downloads, subscriptions, and support for multiple services, NewPipe provides a comprehensive set of features without requiring Google Play Services.

Free

Download

Software Informations:
Developer:
Team NewPipe.
Operating System:
Android
Date Added:
2026-11-08T06:07:20.543Z