DBX is an open-source cross-platform database client designed to connect to a wide range of databases from a single application. It supports more than 100 database and data services, including PostgreSQL, MySQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, Oracle, Cloudflare D1, and ClickHouse.

The project goes beyond traditional database management tools by combining a native desktop application with Docker and web deployments, a command-line interface, AI-assisted SQL, and Model Context Protocol support for AI coding agents.

Features

DBX provides a database browser with support for schemas, tables, columns, indexes, foreign keys, and triggers. Its query editor is based on CodeMirror 6 and includes SQL syntax highlighting, metadata-aware autocomplete, query history, saved SQL snippets, formatting, and diagnostics.

Key features include:

  • Support for 100+ databases and data services

  • PostgreSQL, MySQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, Oracle, and more

  • Cloudflare D1 support

  • SQL editor with autocomplete

  • SQL formatting and diagnostics

  • Query history

  • Saved SQL snippets

  • Data grid with virtual scrolling

  • Inline data editing

  • SQL preview before saving changes

  • Filtering and sorting

  • Full-text search

  • CSV, JSON, Markdown, XLSX, and SQL INSERT exports

  • Schema browser

  • Database search

  • AI SQL assistant

  • SQL explanation and optimization

  • AI-generated SQL safety checks

  • Claude, OpenAI, Ollama, and OpenAI-compatible model support

  • MCP server

  • CLI

  • Docker deployment

  • Web interface

  • Plugin ecosystem

  • Kafka, RabbitMQ, Pulsar, MQTT, and other middleware consoles

The AI integration is particularly notable. Users can describe a database operation in natural language and have DBX generate SQL, explain existing queries, optimize them, or help diagnose errors. DBX also applies safety checks to AI-generated SQL before execution.

MCP support allows compatible AI coding tools such as Claude Code, Cursor, and Windsurf to interact with configured databases through DBX. The available operations include listing connections, browsing tables, executing SQL, and opening tables in the DBX interface.

Download DBX v0.6.61 - Software Mirrors

DBX v0.6.61 for Windows

DBX_0.6.61_x64_en-US.msi | 42 MB

DBX_0.6.61_x64-win7-server2012r2-offline-setup.exe | 179.09 MB

DBX_0.6.61_x64-setup.exe | 32.31 MB

DBX_0.6.61_x64-portable.zip | 42.44 MB

DBX_0.6.61_x64-offline-setup.exe | 239.9 MB

DBX_0.6.61_arm64_en-US.msi | 39.88 MB

DBX_0.6.61_arm64-setup.exe | 29.72 MB

DBX_0.6.61_arm64-portable.zip | 40.46 MB

DBX_0.6.61_arm64-offline-setup.exe | 213.72 MB

DBX v0.6.61 for macOS

DBX_0.6.61_x64.dmg | 46.83 MB

DBX_0.6.61_arm64.dmg | 43.03 MB

DBX v0.6.61 for Linux

DBX_0.6.61_arm64.rpm | 45.14 MB

DBX_0.6.61_arm64.deb | 45.13 MB

DBX_0.6.61_arm64.AppImage | 114.3 MB

DBX_0.6.61_amd64.deb | 46.71 MB

DBX_0.6.61_amd64.AppImage | 117.52 MB

DBX-0.6.61-1.x86_64.rpm | 46.7 MB

Others Download related to DBX v0.6.61

DBX_x64.app.tar.gz | 46.87 MB

DBX_0.6.61_x64-browser-static.tar.gz | 42.17 MB

DBX_0.6.61_fnos.fpk | 79.3 kB

DBX_0.6.61_arm64.app.tar.gz | 43.34 MB

DBX_0.6.61_arm64-browser-static.tar.gz | 40.36 MB

dbx-web_0.6.61_x86_64-browser-static.zip | 40.31 MB

dbx-jdbc-plugin-latest.zip | 9.27 MB

dbx-jdbc-plugin-0.1.50.zip | 9.27 MB

DBX v0.6.61 Source Code

DBX v0.6.61 Source code (zip)

DBX v0.6.61 Source code (tar.gz)

DBX v0.6.61 Release Notes:

v0.6.61 为 v0.6.60 的紧急修复版本，包含 v0.6.60 的其他更新。

修复

  • 回退插件工作台非活动标签页布局保留改动，恢复此前的标签页挂载和切换行为 (contributed by @eryajf) (PR #13831)
查看自 v0.6.59 以来的全部变更

Performance and Compatibility

DBX is built with Tauri 2, Vue 3, TypeScript, and Rust. Its backend uses technologies including SQLx, Tiberius, Redis libraries, and MongoDB support. The project emphasizes a small application footprint and states that the desktop application is approximately 25 MB without a bundled Java runtime, Python environment, or Chromium browser.

Native applications are available for Windows, macOS, and Linux. DBX can also run as a Docker-hosted web application, making it possible to provide database access through a browser or deploy it on a server. Published Docker images support both amd64 and arm64 architectures.

The Docker deployment stores application data in a persistent volume, while connection, plugin, AI, and tunnel credentials are encrypted before being stored in the DBX database. Desktop builds additionally use the operating system's credential storage facilities, including Windows Credential Manager, macOS Keychain, and Linux Secret Service.

The breadth of supported databases is a major advantage, but support is not necessarily identical across every connector. DBX uses a combination of native drivers and agent-based profiles, so the available capabilities can vary depending on the database and connection method.

System Requirements

DBX supports:

  • Windows

  • macOS

  • Linux

  • Docker

  • Web browsers through the self-hosted web interface

The desktop application is designed to run without a separate Java runtime, Python environment, or bundled Chromium installation.

Docker deployments support both amd64 and arm64 architectures.

For Windows, the project provides an MSI installer and also supports installation through Scoop and WinGet. macOS users can install it through Homebrew or a DMG package, while Linux users can use Flatpak or the available release packages.

Pros and Cons

Pros

  • Free and open source

  • Supports 100+ databases and services

  • Lightweight native desktop application

  • Windows, macOS, and Linux support

  • Docker and web deployment

  • SQL editor with autocomplete and formatting

  • Data editing and filtering

  • Multiple export formats

  • AI SQL assistant

  • Ollama support for local AI

  • MCP server

  • CLI

  • AI coding agent integration

  • PostgreSQL, MySQL, SQLite, Redis, MongoDB, and DuckDB support

  • Cloudflare D1 support

  • Middleware and message queue consoles

  • Plugin ecosystem

  • Encrypted credential storage

Cons

  • The large number of supported systems can make the interface and feature set feel complex

  • Functionality can differ between native and agent-based database connectors

  • AI features require an external or local model

  • Advanced MCP and CLI workflows require additional configuration

  • A broad feature set means it can take time to learn the application

How to Install

DBX provides several installation methods.

On Windows, install it through WinGet:

winget install t8y2.dbx

Scoop is also supported:

scoop bucket add dbx https://github.com/t8y2/scoop-bucket
scoop install dbx

On macOS, install it through Homebrew:

brew install --cask dbx

Linux users can install DBX through Flatpak or download the appropriate package from the project's releases.

For a self-hosted web deployment, Docker can be used:

docker run -d --pull=always --name dbx -p 4224:4224 \
  -v dbx-data:/app/data \
  t8y2/dbx:latest

The web interface is then available on port 4224. Docker Compose deployment is also supported.

After installation, create a database connection, enter the required credentials, and use the schema browser or SQL editor to begin working with the database.

Final Verdict

DBX is a broad database management tool that combines conventional database-client functionality with newer AI and developer-oriented capabilities. Its support for more than 100 databases, native desktop applications, Docker deployment, CLI, and web interface makes it suitable for users who regularly work across different database systems.

The AI and MCP integration is one of its more distinctive features. Instead of treating AI as a separate chatbot, DBX can expose configured database connections to compatible AI agents and let them browse schemas or execute SQL through an MCP interface.

Its lightweight Tauri and Rust architecture is also appealing for users who want a database client without the heavier runtime requirements associated with some established alternatives. However, the sheer breadth of supported databases and features means that connector capabilities and workflows can vary, and advanced AI or MCP functionality requires additional configuration.

DBX v0.6.61
Free
Download

Software Informations:
Developer:

Operating System:
Windows / macOS / Linux
Date Added:
2026-10-29T09:07:58.699Z

OpenNext Cloudflare refers to the @opennextjs/cloudflare adapter, which transforms a Next.js application into a format that can run on Cloudflare Workers.

Instead of rewriting your app, it takes the build output and converts it into a Worker-compatible package.

In simple terms:

  • Next.js builds your app

  • OpenNext transforms it

  • Cloudflare Workers runs it globally at the edge

Get Started

New apps

To create a new Next.js app, pre-configured to run on Cloudflare using @opennextjs/cloudflare, run:

npm create cloudflare@latest -- my-next-app --framework=next --platform=workers

Existing Next.js apps

The easiest way to convert an existing Next.js app is to use the migrate command:

npx @opennextjs/cloudflare migrate

This command automates all the setup steps below. If R2 is enabled on your account, it also creates an R2 bucket for caching. See the CLI documentation for more details.

OpenNext Cloudflare 1.20.14 Release Notes

Patch Changes

See details at
  • Export the code patch test utilities as @opennextjs/aws/build/patch/testUtils.js
The inlined manifests were re-created on every load, so apps with large manifests (e.g. the prerender manifest) spent CPU time building and garbage collecting the same objects and kept multiple copies in memory.
  • #1470 7460f53 Thanks @vicb! - fix: scope the module-loading signal to the request on Next 16
Starting with Next.js 16, the module-loading patch silently stopped matching the changed CacheSignal constructor. Concurrent requests could then fail with Cannot perform I/O on behalf of a different request and return truncated responses. Scope the signal to each request again so concurrent renders complete.

How It Works

The process is straightforward but powerful:

  1. You build your Next.js app normally

  2. OpenNext processes the build output

  3. The adapter converts it into a Worker bundle

  4. You deploy it using Wrangler to Cloudflare

This transformation step is the key innovation, enabling Next.js apps to run outside their native ecosystem.

Key Features of OpenNEXT Cloudflare

1. Full Next.js Feature Support

OpenNext Cloudflare supports most major Next.js features:

  • Server-side rendering (SSR)

  • Static site generation (SSG)

  • Incremental static regeneration (ISR)

  • API routes and middleware

  • App Router and React Server Components

This makes it suitable for real production apps, not just simple sites.

2. Node.js Runtime on Cloudflare Workers

Unlike older approaches, OpenNext uses a Node-compatible runtime inside Workers. This allows broader compatibility with existing Next.js apps.

This is a major advantage over edge-only solutions that restrict APIs.

3. Global Edge Deployment

By using Cloudflare Workers, your app runs close to users worldwide, improving latency and performance.

This is especially useful for:

  • SaaS apps

  • APIs

  • Global websites

4. Advanced Caching with R2

OpenNext integrates with Cloudflare R2 for caching features like ISR, helping reduce rebuild costs and improve response times.

5. Multi-Worker Architecture (Advanced)

You can split your app into multiple Workers for better performance and scalability, although this requires advanced configuration.

Performance and Real-World Behavior

OpenNext Cloudflare delivers strong global performance thanks to edge execution. However, performance depends heavily on caching configuration.

For example:

  • Static assets are served efficiently from CDN

  • Dynamic routes use Workers for SSR

  • Improper caching can increase CPU usage

This means optimization is critical for best results.

Developer Experience

Setting up OpenNext Cloudflare is more complex than traditional deployment.

Typical setup includes:

  • Installing @opennextjs/cloudflare

  • Configuring Wrangler

  • Managing cache and storage

  • Adjusting runtime settings

There is also a key limitation:

  • Edge runtime is not fully supported yet, requiring Node runtime instead

This adds some constraints depending on your app architecture.

Pros and Cons

Pros

  • Deploy Next.js on Cloudflare Workers

  • Avoid vendor lock-in from platforms like Vercel

  • Supports most Next.js features

  • Global edge performance

  • Open source and flexible

Cons

  • Setup complexity is high

  • Requires understanding of Cloudflare ecosystem

  • Some features still evolving

  • Windows support is limited

  • Caching and ISR require careful tuning

OpenNext Cloudflare vs Vercel

While Vercel offers the easiest Next.js deployment, OpenNext Cloudflare provides:

  • More infrastructure control

  • Multi-cloud flexibility

  • Potential cost optimization at scale

However, Vercel still wins in simplicity and developer experience.

Who Should Use OpenNext Cloudflare

This setup is ideal for:

  • Advanced developers and DevOps teams

  • Companies avoiding vendor lock-in

  • Projects needing global edge performance

  • Teams already using Cloudflare ecosystem

It is not ideal for beginners or small projects that need quick deployment.

Final Verdict

OpenNext Cloudflare is a powerful solution that unlocks true portability for Next.js applications on edge infrastructure. It brings together flexibility, performance, and control, but at the cost of complexity.

If you want full control over deployment and global performance, OpenNext Cloudflare is one of the most compelling options available today.

If you want to run Next.js apps on Cloudflare instead of being tied to a single platform, OpenNext Cloudflare is one of the most important solutions today. It combines the flexibility of OpenNext with the global edge infrastructure of Cloudflare.

OpenNext Cloudflare 1.20.14
Free
Download

Software Informations:
Developer:

Operating System:
Framework
Date Added:
2026-10-29T08:07:26.095Z

Among the biggest problems of computer find undoubtedly viruses. It is always advisable to have a good antivirus, but in cases where for some reason it is not available and the computer has been infected, we can use some software like Trellix Stinger.

Trellix Stinger has scored a very important both as simply running it gets removed a huge amount of virus actually extended. Thus, we give a breather to install a real antivirus with the computer completely free of worms. McAfee Stinger can remove Backdoor virus spread, Bagle, MyDoom, Sober, Zafi, Korgo, Bugbear, EPO and many more.

The amount of virus that recognizes and eliminates this software is really huge, which makes it one of the most efficient disinfection programs. Trellix Stinger interface is very simple and similar to the window scanner to open the vast majority of antivirus which shows the files that are being reviewed and viruses found.

Furthermore, it allows the analysis exactly configure and check the list of known viruses. Stinger is a type of missile developed in the United States and used by many armies, so if you want to kill viruses with guns, Trellix Stinger is a good software to start.

Trellix Stinger Download Link:

New Detections:
-	Exploit-CVE2020-1058
-	Exploit-CVE2020-1060.a
-	Exploit-CVE2020-1060.b
-	Exploit-cve2020-1062.a
-	Exploit-cve2020-1135
-	Exploit-cve2020-1143.a
-	Exploit-cve2020-1153.a
-	FlyStudio-Agent
-	Generic exploit.ma
-	Generic trojan.kf
-	Generic trojan.kg
-	Generic trojan.kk
-	Generic trojan.ky
-	LNK/Downloader.ch
-	Ransom-LockBit
-	Ransom-Sodnkibi
-	Trojan-AutoIt.p
-	Trojan-BlueNoroff
-	Trojan-Packed.c


Enhanced Detections:
-	Coinminer.l
-	Exploit-CVE2019-1367
-	FakeAV-DZ
-	Generic Trojan.arc
-	Generic Trojan.kg
-	Generic Trojan.li
-	Generic Trojan.lj
-	Generic Trojan.ll
-	Generic trojan.jz
-	Generic trojan.kh
-	Generic-Trojan.z
-	PS/Agent.bv
-	Trojan-AitInject.aq
-	Trojan-CoinMiner.n
-	Trojan-PWS.k
-	Trojan-Ransom.a
-	Trojan-Ransom.b
-	Trojan-Trickbot.d
-	VBObfus.g
Trellix Stinger (Formerly McAfee Stinger) 26.10.44.1
Free
Download

Software Informations:
Developer:

Operating System:
Windows
Date Added:
2026-10-29T08:07:25.858Z

PdfCraft is a free, open-source PDF application designed as an alternative to Adobe Acrobat. Built from scratch in Rust, it combines PDF viewing, document organization, page management, file merging, splitting, and encryption tools in a native desktop application.

Unlike cloud-based PDF services, PdfCraft is designed to process documents locally without requiring an account, telemetry, or cloud processing. It supports Windows, macOS, Linux, and FreeBSD, with a WebAssembly version that runs in a browser.

PdfCraft is particularly interesting for users who want a lightweight, privacy-focused PDF workbench without a subscription. However, it is still an early-stage project, and users who depend on advanced PDF editing, digital signatures, or OCR should consider its current limitations before adopting it.

Features

PDF Viewing and Search

PdfCraft provides a document viewer with text selection, page navigation, and search-as-you-type functionality. Its text selection follows the document's reading order, making it easier to select and copy content from complex layouts.

The renderer is designed to handle international text, vertical Japanese writing, color emoji, and transparency. The application also includes a dark theme and two-page reading mode for a more comfortable reading experience.

A command palette provides quick access to tools and commands, reducing the need to navigate through multiple menus.

Organize and Rearrange Pages

PdfCraft includes a visual page organizer that makes managing PDF documents straightforward. Users can rotate, delete, insert, and reorder pages, with undo support for reversing changes.

These tools are useful for rearranging reports, removing unwanted pages, correcting scanned documents, and assembling documents in the desired order.

The application also supports incremental editing and atomic saves, alongside autosave and crash recovery features designed to reduce the risk of losing work.

Merge, Extract, and Split PDFs

PdfCraft allows users to combine multiple PDF files into a single document, extract selected pages, and split documents into smaller files.

Its document-processing engine aims to preserve important PDF structures during these operations, including links, form fields, layers, and bookmarks.

This makes it useful for administrative work, combining reports, preparing documents for submission, and separating large files into manageable sections.

However, complex documents should be checked after processing to ensure that their formatting and interactive elements remain intact.

PDF Security and Encryption

PdfCraft supports opening encrypted PDF files using older RC4 encryption and modern AES-256 encryption.

It also respects document permissions specified by the author. This is useful when working with protected documents that restrict certain operations.

Encryption support does not mean that PdfCraft provides every security feature available in professional PDF software. Users who require certificate-based digital signatures, advanced redaction, or specialized document-security workflows should verify those capabilities separately.

Forms, Layers, and Document Structure

PdfCraft is designed to preserve PDF features beyond ordinary page content. These include form fields, layers, links, and bookmarks when combining or splitting documents.

This is important because PDF files often contain interactive elements and structural information that can be lost when processed by simpler PDF utilities.

The project emphasizes document integrity, although its developers acknowledge that its rendering quality has not yet been comprehensively compared against Adobe Acrobat.

Command-Line Tools and AI Automation

PdfCraft includes a command-line interface for inspecting documents, extracting text, rendering pages, editing PDF files, combining documents, extracting pages, and splitting files.

For example, you can inspect a PDF's structure in JSON format:

pdfcraft-cli info document.pdf

Extract text from a specific page:

pdfcraft-cli text document.pdf --page 3

Rotate pages, delete a page, and update the document title:

pdfcraft-cli edit input.pdf \
  --rotate 1,2:90 \
  --delete 5 \
  --title "Q3" \
  --out output.pdf

These capabilities make PdfCraft useful for batch processing, scripts, and automated document workflows. Its agent-oriented architecture also makes it suitable for integration with compatible AI tools.

Download PdfCraft v0.15.0 - Software Mirrors

PdfCraft v0.15.0 for Windows

pdfcraft-0.15.0-windows-x86.msi | 85.23 MB

pdfcraft-0.15.0-windows-x86-portable.zip | 101.63 MB

pdfcraft-0.15.0-windows-x64.msi | 87.09 MB

pdfcraft-0.15.0-windows-x64-portable.zip | 106.29 MB

pdfcraft-0.15.0-windows-arm64.msi | 83.1 MB

pdfcraft-0.15.0-windows-arm64-portable.zip | 101.97 MB

PdfCraft v0.15.0 for macOS

pdfcraft-cli-0.15.0-macos-universal.zip | 80.08 MB

pdfcraft-0.15.0-macos-universal.dmg | 116.21 MB

PdfCraft v0.15.0 for Linux

pdfcraft-cli-0.15.0-linux-x86_64.tar.gz | 39.8 MB

pdfcraft-cli-0.15.0-linux-aarch64.tar.gz | 38.31 MB

pdfcraft-0.15.0-linux-x86_64.tar.gz | 105.17 MB

pdfcraft-0.15.0-linux-x86_64.rpm | 105.7 MB

pdfcraft-0.15.0-linux-x86_64.pkg.tar.zst | 82.08 MB

pdfcraft-0.15.0-linux-x86_64.flatpak | 77.98 MB

pdfcraft-0.15.0-linux-x86_64.deb | 106.2 MB

pdfcraft-0.15.0-linux-x86_64.AppImage.zsync | 175.29 kB

pdfcraft-0.15.0-linux-x86_64.AppImage | 100.03 MB

pdfcraft-0.15.0-linux-riscv64.tar.gz | 102.85 MB

pdfcraft-0.15.0-linux-riscv64.rpm | 103.38 MB

pdfcraft-0.15.0-linux-riscv64.deb | 103.69 MB

pdfcraft-0.15.0-linux-aarch64.tar.gz | 101.55 MB

pdfcraft-0.15.0-linux-aarch64.rpm | 102.82 MB

pdfcraft-0.15.0-linux-aarch64.pkg.tar.zst | 79.72 MB

pdfcraft-0.15.0-linux-aarch64.flatpak | 74.08 MB

pdfcraft-0.15.0-linux-aarch64.deb | 103.44 MB

pdfcraft-0.15.0-linux-aarch64.AppImage.zsync | 169.13 kB

pdfcraft-0.15.0-linux-aarch64.AppImage | 96.51 MB

PdfCraft v0.15.0 for BSD

pdfcraft-0.15.0-freebsd-x86_64.tar.gz | 104.58 MB

Others Download related to PdfCraft v0.15.0

pdfcraft-web-0.15.0.zip | 16.26 MB

PdfCraft v0.15.0 Source Code

PdfCraft v0.15.0 Source code (zip)

PdfCraft v0.15.0 Source code (tar.gz)

PdfCraft v0.15.0 Release Notes:

What's Changed

  • Reject non-hex characters in XFA image hash parsing by @Silvertree2010 in #4630
  • Fix AFNumber format printing "inf" for large finite values by @Silvertree2010 in #4592
  • Reject '+' as a hex digit in FormCalc url Decode escapes by @Silvertree2010 in #4586
  • Fix FormCalc Round overflowing to infinity for large values by @Silvertree2010 in #4508
  • M7: dotted day-first dates in header and footer by @Hagma2023 in #4503
  • fix(xfdf): an imported FDF comment's pop-up is placed on the page, not copied in as a direct dictionary by @marcoarnulfo in #4493
  • fix(platform): a saved file keeps its hidden and system attributes on Windows by @FriedCerebrum in #4647
  • fix(edit): resizing an image under a shared clip scales its own clip too by @meethere in #4639
  • M3: the accessible window is named with the window title (#4614) by @Lcoding15 in #4640
  • M6: a round XFA check box's field highlight is round, as a radio button's is by @EricKaden in #4512
  • fix(xfdf): an empty field in imported XFDF clears the field, as FDF and XML do by @marcoarnulfo in #4483
  • M7.5: crop an added image by more than half from one side by @Hagma2023 in #4521
  • M9: name a laid-out XFA form's signature fields by their SOM path, so other viewers find the signature by @EricKaden in #4507
  • M3: give the kept button release back before the pointer leaves (Wayland) by @bmh129 in #4500
  • Tests: XFA calculation tests no longer fail when the machine is busy by @dotCooCoo in #4535
  • i18n(fa): add Persian interface translation by @shahriar-hd in #4558
  • M6: a static XFA form whose data fills thousands of fields opens in seconds (#4637) by @mtlcl410 in #4638
  • M4: Document Properties reads a named opening destination's page, so choosing page 1 replaces it (ISO 32000-2 12.3.2.4) by @mtlcl410 in #4574
  • M7: a moved text box's drag preview shows the box alone (#4464) by @mtlcl410 in #4475
  • M2: a luminosity soft mask in a DeviceCMYK group converts as ISO 32000-2 10.4.2 says, so 100% K masks fully by @mtlcl410 in #4423
  • M3: an attachment's row opens on a double-click and has a right-click menu (#3466) by @Lcoding15 in #4513
  • M10: Word export keeps an italic run inside its sentence's paragraph (#4158) by @mtlcl410 in #4411
  • M6: with NeedAppearances, check boxes and radio buttons draw their /MK caption (ISO 32000-2 Table 224) by @mtlcl410 in #4454
  • M3: a Page tools menu in the Pages panel (#4415) by @Lcoding15 in #4583
  • refactor(ui): side panels on craft-ui task panes and the shared rail by @aiongg in #4606
  • Migrate PdfCraft to egui 0.37 by @skylartaylor in #4591
  • feat: startup update prompt modal and direct self-updating by @dylanmtaylor in #4654
  • proposal(redact): prevent retention of confidential vector paths behind clipping (F-008) by @dylanmtaylor in #4577
  • build: pin craft-update to craft-libs main (495e597) by @dylanmtaylor in #4721
  • build: pin craft-update to craft-libs main (495e597) by @dylanmtaylor in #4728
  • chore(deps): bump 11 safe dependency updates by @skylartaylor in #4737
  • test(ui): CJK interface tests skip without craft-fonts by @aiongg in #4706
  • feat(ui): menus from craft-menu, native on macOS by @aiongg in #4752
  • refactor(engine): split lib.rs into modules by @alehel in #4730
  • proposal(redact): unlink unused Type 3 glyph programs and fonts on redaction (F-011) by @dylanmtaylor in #4579
  • fix(sonar): clear css:S9441 and S3776 in forms actions by @dylanmtaylor in #4747
  • ci: require nextest 0.9.150 by @skylartaylor in #4880
  • refactor: shared module layout (craft-contrib#20) by @aiongg in #4889
  • perf(engine): export page images on worker threads (about 80% less wall time) by @Silvertree2010 in #5026
  • Packaging: fetch OCR models from the ONNX URLs (legacy RTEN URLs return 403) by @Jeremy8776 in #5039
  • refactor(ui): use craft-ui's ComboBox for every dropdown by @aiongg in #4988
  • Windows installation policy: PdfCraft by @Jeremy8776 in #4892
  • Enforce Rust coding standards via Clippy by @dylanmtaylor in #4897
  • deps: pin craft-libs at e11f9d9a (craft-menu loads on Cargo before 1.99) by @aiongg in #5094

New Contributors

  • @Hagma2023 made their first contribution in #4503
  • @FriedCerebrum made their first contribution in #4647
  • @shahriar-hd made their first contribution in #4558
  • @Jeremy8776 made their first contribution in #5039
Full Changelog: v0.14.0...v0.15.0

Performance and Compatibility

PdfCraft is written in Rust, with its PDF parsing, rendering, and editing logic organized into reusable libraries. The graphical interface is built on top of this underlying engine.

The project emphasizes faithful document rendering, reliable file operations, and local processing. Its developers report zero crashes across a test corpus of 983 PDF files, although this result should not be interpreted as a guarantee of compatibility with every PDF document.

Supported platforms include Windows, macOS, Linux, FreeBSD, and modern web browsers through WebAssembly. Available packages include Windows installers and portable archives, a universal macOS disk image, Linux AppImage packages, Debian packages, RPM packages, and other distribution formats.

PdfCraft is still in early development. Its roadmap identifies renderer improvements, stronger compatibility testing, editing existing PDF content, digital signatures, OCR, Office-related workflows, preflight tools, and XFA support as areas for further development.

Consequently, it is best viewed as a promising PDF workbench rather than a complete replacement for every Adobe Acrobat workflow.

System Requirements

  • Operating systems: Windows, macOS, Linux, and FreeBSD.

  • Browser support: WebAssembly build for modern browsers.

  • Windows architectures: x86, x64, and ARM64.

  • Linux architectures: x86-64 and ARM64.

  • macOS: Universal build for Intel and Apple silicon.

  • Build requirements: Rust 1.90 or newer, along with the project's documented development dependencies.

The project does not establish a comprehensive minimum RAM or processor specification in the information reviewed. Basic PDF viewing should be suitable for a broad range of modern computers, but performance will depend on document complexity and system resources.

Pros and Cons

Pros

  • Free and open-source under permissive licenses.

  • Native applications for major desktop operating systems.

  • Local document processing without mandatory accounts or cloud uploads.

  • PDF viewing with text search and selection.

  • Page rotation, deletion, insertion, and reordering.

  • PDF merging, extraction, and splitting.

  • Support for encrypted PDFs and document permissions.

  • Designed to preserve links, form fields, layers, and bookmarks.

  • Autosave, crash recovery, and undo support.

  • Command-line tools for scripting and batch processing.

  • WebAssembly version for browser-based use.

Cons

  • Still in early development, with some features planned rather than implemented.

  • PDF rendering quality has not yet been comprehensively benchmarked against Adobe Acrobat.

  • Advanced editing of existing PDF content remains a development priority.

  • Digital signatures, OCR, and specialized document workflows are not yet comprehensive.

  • Compatibility with complex forms and unusual PDF documents requires further testing.

  • Professional publishing and document-preflight capabilities are limited.

How to Install

The easiest way to install PdfCraft is to visit its official website and download the package for your operating system.

Windows users can choose an installer or portable archive. macOS users can download the universal disk image, while Linux users can select AppImage, DEB, RPM, or another available package.

To build PdfCraft from source, install Rust 1.90 or newer and run:

git clone https://github.com/storytold/pdfcraft.git
cd pdfcraft
cargo run --release -p pdfcraft

For command-line PDF processing, build or install the CLI package provided by the project. Consult the official documentation for supported commands, build dependencies, and platform-specific installation instructions.

Final Verdict

PdfCraft is a promising open-source PDF editor for users who want to read, organize, combine, split, and secure documents without relying on a cloud service or paid subscription.

Its strongest advantages are local processing, cross-platform availability, careful handling of PDF structure, and a command-line interface that supports automation. These features make it appealing to developers, privacy-conscious users, and anyone who regularly manages PDF documents.

The main limitation is maturity. PdfCraft does not yet cover every advanced capability offered by established PDF applications, particularly for editing existing content, digital signatures, OCR, and specialized document workflows.

For everyday PDF viewing and organization, PdfCraft is worth trying. Users who need a complete professional PDF solution should evaluate its current feature set against their specific requirements before replacing their existing software.

PdfCraft v0.15.0
Free
Download

Software Informations:
Developer:

Operating System:
Windows / macOS / Linux / BSD
Date Added:
2026-10-29T07:07:18.229Z

Ollama is a local AI runtime that enables users to run popular open source language models such as LLaMA, Mistral, Gemma, and others directly on their system. All processing happens locally, which helps protect sensitive data and reduces dependency on internet connectivity.

It is designed to be minimal, fast, and developer friendly.

Download Ollama 0.40.13 - Software Mirrors

Download Ollama 0.40.13
for Windows
PowerShell: irm https://ollama.com/install.ps1 | iex

Download Ollama 0.40.13
for macOS
sh (macOS or Linux): curl -fsSL https://ollama.com/install.sh | sh

Download From GitHub

Download Ollama 0.40.13 for Windows
OllamaSetup.exe | 1.56 GB

Download Ollama 0.40.13 for macOS
Ollama.dmg | 219.85 MB

Download Ollama 0.40.13 for Windows ARM64
ollama-windows-arm64.zip | 205.93 MB

Download Ollama 0.40.13 for Windows AMD64
ollama-windows-amd64.zip | 1.49 GB

Download Ollama 0.40.13 for Windows AMD64
ollama-windows-amd64-rocm.zip | 245.17 MB

Download Ollama 0.40.13 for Windows AMD64
ollama-windows-amd64-mlx.zip | 881.43 MB

Download Ollama 0.40.13 for Linux ARM64
ollama-linux-arm64.tar.zst | 1.47 GB

Download Ollama 0.40.13 for Linux ARM64
ollama-linux-arm64-jetpack6.tar.zst | 260.71 MB

Download Ollama 0.40.13 for Linux ARM64
ollama-linux-arm64-jetpack5.tar.zst | 287.58 MB

Download Ollama 0.40.13 for Linux AMD64
ollama-linux-amd64.tar.zst | 1.42 GB

Download Ollama 0.40.13 for Linux AMD64
ollama-linux-amd64-rocm.tar.zst | 1003.6 MB

Download Ollama 0.40.13 for Linux AMD64
ollama-linux-amd64-mlx.tar.zst | 1.15 GB

Download Ollama 0.40.13 for macOS
Ollama-darwin.zip | 219.13 MB

Download Ollama 0.40.13 for macOS
ollama-darwin.tgz | 178.04 MB

Download Ollama 0.40.13 for macOS and Linux sh
install.sh | 15.53 kB

Download Ollama 0.40.13 for Windows PowerShell
install.ps1 | 22.1 kB

Ollama 0.40.13 Release Notes:

LFM3 on Linux and Windows

Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni, now run on Linux and Windows as well as Apple silicon. Full Changelog: v0.40.12...v0.40.13

Key Features of Ollama

Ollama focuses on simplicity and performance.

Main features include:

  • Run large language models fully offline

  • Simple command line interface

  • Built in model management and downloads

  • Support for popular open source LLMs

  • Optimized inference on CPU and GPU

  • Local REST API compatible with OpenAI style endpoints

  • Cross platform support

These features make Ollama easy to integrate into development workflows.

Supported Platforms and Hardware

Ollama is available on:

  • macOS

  • Linux

  • Windows

Hardware requirements depend on the model size. Smaller models can run on CPUs, while larger models benefit from GPUs with sufficient VRAM. Ollama automatically optimizes performance based on available hardware.

Performance and Reliability

Ollama is optimized for efficient local inference. It starts quickly, uses system resources effectively, and handles long running sessions reliably.

Model performance varies depending on the chosen model and system specifications, but overall stability is strong.

Ease of Use

Ollama is very easy to use for developers and technical users. Running a model often requires only a single command. The local API server allows seamless integration with applications, scripts, and development tools.

Non technical users may prefer graphical alternatives, but Ollama remains straightforward once basic commands are learned.

Is Ollama Safe to Use

Yes, Ollama is safe when downloaded from the official source. All model execution is local, and no data is sent to external servers unless explicitly configured by the user.

This makes Ollama suitable for private and sensitive workloads.

Pros and Cons of Ollama

Pros:

  • Fully offline and privacy friendly

  • Simple installation and usage

  • Lightweight and fast

  • Strong developer API support

  • Wide range of supported models

Cons:

  • Command line focused interface

  • No built in graphical UI

  • Performance depends on hardware

Despite these limitations, Ollama is widely respected in the local AI community.

Common Use Cases

Ollama is commonly used for:

  • Local AI chat assistants

  • Software development and code generation

  • Research and experimentation

  • Private AI workflows

  • API based AI integrations

Its simplicity makes it ideal for rapid testing and deployment.

Final Verdict

Ollama is an excellent solution for running large language models locally with minimal setup. It prioritizes privacy, speed, and developer control while staying lightweight and efficient.

For users comfortable with the command line and API based tools, Ollama is one of the best local AI runtimes available.

Ollama is a lightweight tool that allows users to run large language models locally on their own computer. It is popular among developers, researchers, and privacy focused users who want full control over AI models without relying on cloud based services.

Ollama simplifies the process of downloading, running, and managing local AI models through a simple command line and API.

Ollama 0.40.13
Free
Download

Software Informations:
Developer:

Operating System:
Windows / macOS / Linux
Date Added:
2026-10-29T07:07:18.132Z

At its core, Brave Browser is built on the open-source Chromium engine, ensuring compatibility with most websites and extensions from the Chrome Web Store. However, what sets it apart is its aggressive stance on privacy. Out of the box, Brave blocks third-party ads, trackers, cookies, and fingerprinting techniques that websites use to profile users.

  • Shields Protection: Brave's signature feature is "Shields," a customizable panel that lets users adjust blocking levels per site. It categorizes threats into ads, trackers, upgrades to HTTPS, and even script blocking. According to Brave's own transparency reports, the browser blocks billions of tracking attempts daily across its user base.

  • Tor Integration: For ultimate anonymity, Brave includes a private window with Tor, routing traffic through the Tor network to mask IP addresses. This is particularly useful for journalists, activists, or anyone in restrictive regimes.

Download Brave Browser Release v1.98.62 (Chromium 156.0.8078.74) Offline Installer

Windows

macOS

Installer - 64bit (160.2 MB)

Installer - 32bit (149.93 MB)

Installer - ARM64 (164.35 MB)

Silent Installer - 64bit (160.2 MB)

Silent Installer - 32bit (149.93 MB)

Silent Installer - ARM64 (164.35 MB)

Installer - 64bit (139.07 MB)

Installer - 32bit (128.92 MB)

Installer - ARM64 (144.1 MB)

Silent Installer - 64bit (139.07 MB)

Silent Installer - 32bit (128.93 MB)

Silent Installer - ARM64 (144.08 MB)

DMG - ARM64 (221.41 MB)

PKG - ARM64 (212.88 MB)

DMG - Universal (325.06 MB)

PKG - Universal (313.24 MB)

DMG - AMD64 (239.31 MB)

PKG - AMD64 (230.19 MB)

DMG - ARM64 (163.7 MB)

PKG - ARM64 (154.87 MB)

DMG - Universal (260.1 MB)

PKG - Universal (245.25 MB)

DMG - AMD64 (178.65 MB)

PKG - AMD64 (170.44 MB)

Linux

Android / IOS

RPM - ARM64 (138.87 MB)

RPM - AMD64 (147.55 MB)

ZIP - AMD64 (202.64 MB)

ZIP - ARM64 (201.91 MB)

DEB - AMD64 (146.01 MB)

DEB - ARM64 (137.42 MB)

RPM - ARM64 (123.54 MB)

RPM - AMD64 (131.53 MB)

ZIP - AMD64 (182.55 MB)

ZIP - ARM64 (182.5 MB)

DEB - AMD64 (129.94 MB)

DEB - ARM64 (122 MB)

brave-core-ios-1.98.62.app.dSYM.zip (670.71 MB)

brave-core-ios-1.98.62.ipa (284.24 MB)

Bravearm64Universal.apk (201.3 MB)

BraveMonoarm.apk (220.52 MB)

BraveMonoarm64.apk (346.32 MB)

BraveMonox64.apk (383.02 MB)

BraveMonox86.apk (294.79 MB)

Brave Browser Release v1.98.62 (Chromium 156.0.8078.74) Offline Installer Release Notes:

Release v1.98.62 (Chromium 156.0.8078.74)

Android

Pick the APK suitable for your device's architecture.

iOS

brave-core-ios-1.98.62.* contains Brave for iOS.

Linux

DEB and RPM packages attached below, details at https://brave.com/linux

macOS

Brave--.dmg or Brave--.pkg will install this version. macOS 12 and above are supported as per https://support.brave.app/hc/en-us/articles/360021357112-What-are-the-system-requirements-to-install-Brave

Windows

Brave*Setup.exe will fetch and install the latest available version for your CPU architecture from our update servers. Windows 10 and above are supported as per https://support.brave.app/hc/en-us/articles/360021357112-What-are-the-system-requirements-to-install-Brave

Release Notes

Origin Release Notes

Unlike incognito modes in other browsers, which merely hide history from your device, Brave prevents data from leaving your machine in the first place.

Privacy doesn't come at the cost of speed. Brave claims to load pages up to 3-6 times faster than competitors by stripping out ad-laden content. Tests conducted by outlets like PCMag and Tom's Hardware in 2024 confirm this: Brave consistently outperforms Chrome in resource usage and load times, especially on ad-heavy sites like news portals.

The browser achieves this through:

  • Ad and Tracker Blocking: Removing bloatware elements reduces data transfer and rendering time.

  • Optimized Resource Management: Lower CPU and RAM usage means smoother multitasking, ideal for low-end devices.

Brave Browser is available on Windows, macOS, Linux, Android, and iOS. Syncing across devices is seamless via end-to-end encryption, without requiring an account.

Key features include:

Brave Search: An independent, ad-free search engine launched in 2021, now powering default searches. It doesn't track queries and offers "Goggles" for custom result filtering.

Brave Wallet: A built-in crypto wallet supporting Ethereum, Solana, and more, with NFT viewing and DeFi integration.

IPFS Support: Peer-to-peer file sharing for decentralized web access.

AI Integration: Brave introduced "Leo," an on-device AI assistant for summarizing pages, translating, or answering queries without cloud tracking.

Brave Browser has emerged as a formidable alternative to mainstream browsers like Chrome, Firefox, and Safari. Launched in 2016 by Brave Software, Inc., co-founded by Brendan Eich the creator of JavaScript and former Mozilla CEO Brave prioritizes user privacy, speed, and a unique ad-reward system. with over 60 million monthly active users, Brave is not just a browser, it's a statement against the pervasive data-tracking economy dominated by tech giants.

Brave Browser Release v1.98.62 (Chromium 156.0.8078.74) Offline Installer
Free
Download

Software Informations:
Developer:

Operating System:
Windows / Mac / Linux
Date Added:
2026-10-29T06:07:15.448Z

Visual Studio Code, commonly known as VSCode, has become one of the most popular development tools in the world. It is lightweight, highly customizable, and packed with features that help developers improve their productivity. Whether you are building web applications, working on backend services, or editing configuration files, VSCode delivers a smooth and powerful experience.

Built for Speed and Flexibility

VSCode is famous for its fast startup time and responsive interface. Developers appreciate how quickly the editor loads even large projects. Its modular design allows users to add only the extensions they need, which keeps the environment clean and efficient. This flexibility makes VSCode suitable for beginners, professionals, and teams managing complex codebases.

Extensions and Ecosystem

The extension marketplace is a huge reason for VSCode’s success. Users can install support for any programming language, framework, or workflow. Popular extensions include

  • Git integration

  • Docker tools

  • Python, JavaScript, Java, Go, and C extensions

  • Themes and UI customization

  • Remote development tools

This ecosystem allows developers to tailor the editor to match their exact needs without overwhelming them with unnecessary features.

Productivity Driven Features

VSCode includes advanced features that help developers write code faster and with fewer errors. These include

  • Intelligent code completion

  • Real time diagnostics

  • Integrated terminal

  • Debugging environment

  • Built in source control

  • Snippet support

The editor focuses on delivering a comfortable and intuitive coding experience, making it easier for developers to stay focused and productive.

Ideal for Solo Developers and Teams

VSCode’s collaborative features have grown significantly. With Live Share, developers can work together in real time without needing additional tools. The editor also integrates seamlessly with GitHub and Azure services, making it a great option for remote teams or open source contributors.

Performance and Stability

Despite being lightweight, VSCode handles large projects well. It runs smoothly across Windows, macOS, and Linux, ensuring that developers on any platform can maintain a consistent workflow. Regular updates also ensure new features, performance improvements, and bug fixes arrive quickly.

Final Verdict

Visual Studio Code stands out as one of the best code editors available today. Its mix of speed, customization, and tooling support makes it an excellent choice for almost every type of developer. Whether you are writing a quick script or managing enterprise level code, VSCode delivers reliability and power.

VSCode continues to evolve and remains the editor of choice for millions of developers worldwide.

Some of the key highlights include in VSCode version 1.107.1:

  • Improved out of the box experience with Agent Sessions sidebar. The default view session orentation is not set to sideBySide.

  • Improved Input Needed request rendering on Agent Sessions.

  • Support copying workspace changes when creating Background Session

  • New session does not clear input/prompt.

  • Tool calls in Cloud sessions are collapsed by default now.


Visual Studio Code (VSCode) 1.144.0
Free
Download

Software Informations:
Developer:

Operating System:
Windows / Mac / Linux
Date Added:
2026-10-29T05:07:16.755Z

Ponytail is an open source tool that changes how AI coding agents approach software development. Its core idea is simple: before writing new code, the agent should first ask whether the code is actually necessary. If it is, Ponytail encourages the agent to reuse existing code, use the standard library, rely on native platform features, or choose the simplest implementation possible.

The philosophy behind Ponytail is based on avoiding unnecessary complexity. Its rules follow a simple progression: check whether something needs to exist, reuse what is already available, use the standard library, use native platform features, use installed dependencies, and only then write the minimum code required. This is essentially YAGNI applied directly to AI coding agents.

This approach addresses a common problem with AI assisted development. Coding agents can sometimes over-engineer relatively simple requirements by adding dependencies, creating unnecessary abstractions, or building components that a platform already provides. Ponytail attempts to keep the agent focused on the simplest solution instead of automatically producing more code.

An important detail is that Ponytail does not simply tell the AI to write fewer lines. The project explicitly separates being lazy from being careless. Validation at trust boundaries, data loss handling, security, and accessibility are not supposed to be removed just to make the code shorter. The agent is expected to understand the problem and existing code before applying the simplicity rules.

The project also provides several ways to integrate Ponytail into AI coding environments. It supports tools including Claude Code, Codex, GitHub Copilot CLI, Pi, OpenCode, Devin, OpenClaw, and several other agent environments. This makes it more flexible than a simple instruction file intended for one particular coding assistant.

The benchmark results are particularly interesting. In the project's agentic benchmark using Claude Code and a real FastAPI plus React repository, Ponytail reduced lines of code by 54 percent, tokens by 22 percent, cost by 20 percent, and execution time by 27 percent compared with the same agent without the skill. The benchmark covered 12 feature tasks with Haiku 4.5.

Those numbers should not be interpreted as guaranteed savings for every project. The results depend on the model, prompt, task, and existing codebase. The project itself notes that a reasoning model can sometimes spend additional tokens thinking through the rules, potentially reducing or reversing the expected savings.

Another positive aspect is that Ponytail is not tied to a particular programming language. Since it works primarily by influencing how the coding agent approaches a task, it can be applied across different languages and frameworks. That makes the concept useful whether you are working on a frontend application, backend service, CLI tool, or another type of software project.

There is also a potential downside. Simplicity is not always the correct answer. Some projects genuinely need abstractions, additional dependencies, or more elaborate architecture. Developers should therefore treat Ponytail as a decision-making guideline rather than an instruction to blindly minimize every implementation.

For experienced developers, this can be particularly useful because it reinforces a mindset that experienced engineers already use: understand the existing system first, avoid unnecessary changes, and solve the actual problem rather than the imagined one.

Download Ponytail v5.3.3 - Software Mirrors

Ponytail v5.3.3 Source Code

Ponytail v5.3.3 Source code (zip)

Ponytail v5.3.3 Source code (tar.gz)

Ponytail v5.3.3 Release Notes:

This one cleans up the band. On Team, Enterprise and managed machines the warning on your first prompt is gone, and the band shows your model and session name again. In VS Code it stays on one line, other plugins' commands no longer print under ponytail's name, and the noisy "duplicate?" hint is gone.

What's Changed

  • fix(band): show the level again after /clear and /resume by @timofeevAV in #1161
  • fix(map): raise the git ls-files buffer so large repos keep tracked files by @HyperionBurn in #1156
  • ci: run agentic benchmark selftest in test workflow by @ml-lubich in #1154
  • docs: clarify Cursor mode state scope by @Boulea7 in #1135
  • fix(codex): small composer icon instead of the 554 KB logo by @DietrichGebert in #1164
  • fix(hooks): 15 s hook timeout so a slow node start on Windows keeps its output by @DietrichGebert in #1165
  • fix(hooks): give the codebase map 3 s so a slow Windows start keeps it by @DietrichGebert in #1166
  • fix(bench): wait for the killed todo server before the workdir cleanup by @devohmycode in #1116
  • fix(band): find the transcript without a classic hook by @trhinehart-attentive in #1242
  • fix(band): watch only /clear, /resume and /branch, so other plugins' output is not labelled ponytail by @ph3on1x in #1291
  • fix(band): size the row to bodyColumns only in the terminal by @lelmarir in #1302
  • fix(band): drop the duplicate? hint, count only project files, tighter details view by @DietrichGebert in #1305
  • chore: release v5.3.3 by @DietrichGebert in #1307

New Contributors

  • @timofeevAV made their first contribution in #1161
  • @HyperionBurn made their first contribution in #1156
  • @ml-lubich made their first contribution in #1154
  • @trhinehart-attentive made their first contribution in #1242
  • @ph3on1x made their first contribution in #1291
  • @lelmarir made their first contribution in #1302
Full Changelog: v5.3.2...v5.3.3

How it works

Before writing code, the agent stops at the first rung that holds:

1. Does this need to exist?   → no: skip it (YAGNI)
2. Already in this codebase?  → reuse it, don't rewrite
3. Stdlib does it?            → use it
4. Native platform feature?   → use it
5. Installed dependency?      → use it
6. One line?                  → one line
7. Only then: the minimum that works

The ladder runs after it understands the problem, not instead of it: it reads the code the change touches and traces the real flow before picking a rung. Lazy about the solution, never about reading.

Lazy, not negligent: trust-boundary validation, data-loss handling, security, and accessibility are never on the chopping block.

Install

The most effort ponytail will ever ask of you:

The Claude Code and Codex plugins run two tiny Node.js lifecycle hooks, so node needs to be on your PATH (note for Nix/nvm users: it must be on the non-interactive shell's PATH). If it isn't, the skills still work, the always-on activation just stays quiet instead of erroring on every prompt.

Claude Code

/plugin marketplace add DietrichGebert/ponytail

/plugin install ponytail@ponytail

(You have to send two separate prompts for the install to work)

Same steps in the Claude Code Desktop app's Code tab: type the two /plugin commands above into the prompt box, or click the + button next to it, choose Plugins → Add plugin to browse your configured marketplaces, and manage marketplaces from Customize in the sidebar.

Codex

codex plugin marketplace add DietrichGebert/ponytail
codex plugin add ponytail@ponytail

Run codex and open /hooks, review and trust its two lifecycle hooks, and start a new thread.

This same install also covers the Codex desktop app: restart the app after installing and it picks up the plugin.

GitHub Copilot CLI

copilot plugin marketplace add DietrichGebert/ponytail
copilot plugin install ponytail@ponytail

In an interactive Copilot CLI session, use the slash equivalents:

/plugin marketplace add DietrichGebert/ponytail
/plugin install ponytail@ponytail

Copilot CLI namespaces plugin commands by plugin name. For example:

/ponytail:ponytail ultra
/ponytail:ponytail-review

Pi agent harness

pi install git:github.com/DietrichGebert/ponytail

OpenCode

Add to opencode.json:

{ "plugin": ["@dietrichgebert/ponytail"] }

Run from a checkout instead (the plugin reuses hooks/ and skills/):

{ "plugin": ["./.opencode/plugins/ponytail.mjs"] }

Injects the ruleset every turn at the active level; adds the /ponytail commands (see Commands). OpenCode also auto-loads this repo's AGENTS.md, so the rules hold even without the plugin. The plugin adds the lite/full/ultra/off levels.

The ./ path resolves against your project's opencode.json; to share one checkout across projects, point it at the absolute path of the .mjs instead (it finds its hooks/ and skills/ relative to its own file).

Gemini CLI

gemini extensions install https://github.com/DietrichGebert/ponytail

Loads the ruleset as always-on context every session and registers the /ponytail commands; the skills/ ship too, activated when a task needs them. The Gemini adapter intentionally does not ship a root hooks/hooks.json: Gemini auto-loads that path, while Ponytail's lifecycle hooks use Claude/Codex event names.

Qoder

Qoder auto-loads AGENTS.md from the repo root as always-on context, so running ponytail from a checkout works with zero setup. For per-project rules, copy .qoder/rules/ponytail.md into your project's .qoder/rules/. The six ponytail skills (/ponytail, /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain, /ponytail-help) are available via Qoder's Skill system; the plugin manifest at .qoder-plugin/plugin.json points at the skills/ directory.

For full plugin-tier support (automatic mode activation + ruleset injection on every prompt), add the hooks from hooks/qoder-hooks.json to your .qoder/settings.json. Replace PONYTAIL_DIR with the path to your ponytail checkout. Qoder's UserPromptSubmit hook activates the default mode on first prompt and injects the ruleset every turn; PreToolUse with task|Task matcher injects the ruleset into subagents. Level switches (/ponytail lite|full|ultra|off) work automatically.

Antigravity CLI

Google is renaming Gemini CLI to Antigravity CLI (the agy binary); the same extension installs there:

agy plugin install https://github.com/DietrichGebert/ponytail

It reuses this repo's gemini-extension.json. One difference: Antigravity converts the /ponytail commands into skills, so you type them into the chat (e.g. /ponytail-review as a message) instead of picking them from a slash menu. Until the migration completes (around June 18, 2026), gemini extensions install still works too. To run it as an always-on rule instead, drop the ruleset into .agents/rules/.

Hermes Agent

hermes plugins install DietrichGebert/ponytail --enable

Restart Hermes after installing. The plugin injects the active Ponytail mode before each LLM turn, registers the bundled skills as ponytail:<skill>, and adds /ponytail, /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain, and /ponytail-help. In shared gateways, restrict /ponytail to trusted users with Hermes slash-command access controls; runtime mode is process-local.

CodeWhale

Reads AGENTS.md from the project root, zero setup. Copy AGENTS.md to your project, or run codewhale from a checkout of this repo. That's it.

Swival

Stage the collection in your library first, then add the skills you want:

swival skills add --global https://github.com/DietrichGebert/ponytail  # stage into ~/.config/swival/library
swival skills add ponytail                                             # install the collection into this project
swival skills add --global ponytail                                    # or activate it in every project

Swival also reads AGENTS.md from the project root and ~/.config/swival/AGENTS.md globally, the instruction-only fallback.

On the command line, use a $ prefix to explicitly activate a skill. For example: $ponytail-review.

Devin CLI

devin plugins install DietrichGebert/ponytail

Installs ponytail as a Devin plugin; skills are available as /ponytail:ponytail, /ponytail:ponytail-review, and so on.

OpenClaw

clawhub install ponytail

Installs ponytail as an OpenClaw skill from ClawHub; the review, audit, debt, gain, and help skills install the same way (clawhub install ponytail-review, and so on). OpenClaw applies it on coding tasks and also exposes it as a /ponytail command. Without ClawHub, copy .openclaw/skills/ponytail into ~/.openclaw/skills/.

Grok Build

grok plugin install DietrichGebert/ponytail --trust

Enable the plugin (off by default): /plugins → Plugins → Space on ponytail, or in ~/.grok/config.toml:

[plugins]
enabled = ["ponytail"]

Start a new session (or reload plugins). Skills show as /ponytail, /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain, /ponytail-help. Verify with grok inspect. Grok can auto-invoke ponytail for coding tasks from its skill description; use /ponytail (or /ponytail lite, /ponytail full, /ponytail ultra) when activation needs to be explicit. Grok lifecycle hooks are not used because their SessionStart output cannot inject instructions.

Pros

  • Encourages simpler AI generated code

  • Reduces unnecessary dependencies and abstractions

  • Applies YAGNI principles to AI coding agents

  • Encourages reuse of existing project code

  • Supports multiple AI coding environments

  • Designed to preserve security and accessibility considerations

  • Open source and MIT licensed

  • Benchmark shows meaningful reductions in code, cost, tokens, and time

Cons

  • Results depend heavily on the AI model and task

  • Simplicity rules can be inappropriate for some complex projects

  • Adds another layer of instructions to the coding workflow

  • Benchmark results should not be treated as universal performance guarantees

Final Verdict

Ponytail is an interesting solution to one of the biggest weaknesses of AI assisted programming: the tendency to build more than necessary. Instead of simply telling an AI agent to produce shorter code, it gives the agent a structured decision process for finding simpler solutions before writing anything.

Its strongest idea is that less code should be a consequence of better engineering decisions, not code golf. Reusing existing functionality, choosing native features, avoiding unnecessary dependencies, and questioning whether a feature needs to exist in the first place can make AI generated software easier to maintain.

For developers who regularly use AI coding agents and are tired of unnecessary abstractions, dependencies, and over-engineered solutions, Ponytail is well worth trying.

Ponytail v5.3.3
Free
Download

Software Informations:
Developer:

Operating System:
All Platforms
Date Added:
2026-10-29T05:07:16.665Z
Subscribe to: Posts (Atom)