Leaderboard

Support for sub-agents has been added in version 7, now posted to GitHub. Your primary agent can now delegate to other agents when it deems it worthwhile. They can be more instances of the same agent, or instance of other agent models you've defined in the module configuration. More details further down. This version also adds a public API method for sharing agent configuration with other modules, which was requested by @psy. To get agent configuration use $at->getAgents(); (to get all) or $at->getPrimaryAgent() to get the primary agent. See the README file (near the bottom) for instructions on how to use it. Each of the returned $agent objects also includes an ask() method, for when you want AgentTools to handle the request/response process for you as well: $agent = $at->getPrimaryAgent(); $answer = $agent->ask('What is the capital of France?'); echo $answer; Claude Code both requested and developed the sub-agents feature and I asked it to describe some examples of when/where it might be used:

The memory feature is now active in AgentTools and it's enabled by default. I have to say it makes the experience a whole lot better. Also, we've updated it so that agents can now decide what API.md files they want to receive, and whether or not they want sitemaps/schema, rather than is sending stuff the may or may not need. So the "Include extra context" setting in engineer is now removed since it's no longer necessary. More coming by Friday.

Looking forwarding to trying out the memory feature @ryan Here's something of related interest: https://github.com/memvid/claude-brain I do love this description of the issue: You: "Remember that auth bug we fixed?" Claude: "I don't have memory of previous conversations." You: "We spent 3 hours on it yesterday" Claude: "I'd be happy to help debug from scratch!"

I made a little update to 1.3.7, bringing it to the current PHP8+ and PW3+ standards. Changes in 1.3.7 (2026-04-22) Updated for ProcessWire 3.x and PHP 8.x compatibility Declared class properties explicitly to fix PHP 8.2 dynamic property deprecation Fixed nullable type hints on render() signature (?array, ?Page) required since PHP 8.0 Replaced global wire() calls with $this->wire() for correct PW3 multi-instance scoping Replaced new PageArray() with $this->wire(new PageArray()) for proper instance binding Replaced object identity comparisons (===) with ID-based comparisons (->id ===) for $is_current and $is_root Replaced loose null comparisons (!= null) with strict (!== null) throughout Fixed misleading single-line if/else in xtemplates block with proper braces Removed unused $v_unformatted variable in parsePlaceholders() Replaced $this->fields / $this->users magic access with $this->wire('fields') / $this->wire('users') Updated getModuleInfo(): added icon, requires (PHP>=8.0, ProcessWire>=3.0.0), updated href to https Bumped version from 1.3.6 to 1.3.7 I only tested it on a site I'm currently working on, and it still works the same. But if you encounter any issues please let me know.

There has been a lot of ProcessWire work covered this week! Here's a summary: 1. AgentTools module has been upgraded with "Site Engineer", an AI agent now built into your admin, and you can ask it questions, create migrations, or have it make other web development updates to your site by going to Setup > Agent Tools > Engineer. To enable the Engineer, you need an Anthropic API key, an OpenAI API key, or an OpenAI compatible API key (apparently several others use the OpenAI key standard). You can optionally put Engineer in "read-only" mode, which is what I do for production sites. In read-only mode, it answers questions and provides you with code for making updates yourself. But if read-only mode is not enabled, then it can act as your web developer and make changes directly, which is what I use with development sites. AgentTools provides full context to Engineer on your site's pages, fields and templates. If using ProcessWire 3.0.258 (or newer) it also provides the new API.md files to help AI know how to best work with all of ProcessWire's Fieldtypes. If you are having Engineer create or manipulate Fields on your site, it's a good idea to have 3.0.258 for the API.md support. Engineer also supports prompt caching for up to 1 hour in order to limit token usage. 2. The AgentTools now has JSON site-map generation features for AI agents. This enables an AI agent to see the full scope of your site. A second site-map feature focuses on all your site's templates and fields, essentially providing the full site schema to the AI agent. 3. In the core, we've added API.md files for all 18 of ProcessWire's core Fieldtypes, except for the comments and cache Fieldtypes, so far. In order to facilitiate this, and to facilitiate AI agent accessibility, all of ProcessWire's Fieldtypes now have their own directories as well. 4. After looking at all the API.md files, it became clear that there was plenty of room for improvement in the APIs of several Fieldtypes, so there have been major core updates to several Fieldtypes, as well as the Fields, Templates and Fieldgroups classes. 5. A Fieldtype testing framework has been built, which tests the full scope of 20 ProcessWire Fieldtypes (all the core ones, plus FieldtypeRepeaterMatrix and FieldtypeTable). It tests field creation, manipulation, traversal (where applicable), sorting (where applicable), searching with selectors, and more. I'll be uploading the testing framework to GitHub soon as well. 6. The new testing framework identified some bugs, which have been fixed. Most notable were selector matching bugs in FieldtypeFloat and FieldtypeDatetime. 7. There has been some refactoring in ProFields FieldtypeRepeaterMatrix and FieldtypeTable, plus API.md files have been generated for both. New versions should be ready soon. In fact, that applies to all of the ProFields, and I hope to cover FieldtypeCombo and FieldtypeCustom next week. 8. ProcessWire 3.0.258 has a whole lot of improvements, changes and fixes in it. Here's the commit log: https://github.com/processwire/processwire/commits/dev/ 9. Back to working on PagesVersionsPro (and have been for a few weeks) but more on that later. 10. There's probably more, but that's all I can remember at the moment. 🙂 Thanks for reading and have a great weekend! Basic examples of using Engineer for migrations:

I guess this one deserves v.2.0, as we got Soma 2.0 back and finally ready for action! And it is a breaking change after all)

I'm using github copilot now since 6 months to do all sort of testing and playing around with various projects. It offers a lot of the different agents, but it's mainly for use with IDE like VS code. I like it a lot and am always surprized at it's capability. Claude is able to help me A LOT updating a very old big online shop to the latest PW (currently local dev only) It has access to powershell to do db stuff and it understood PW very well without much help or special skills. Tho it's great to have it specialize for PW for sure. So I can't use Claude models and some of the others with my github copilot API endpoint with AgentTools, but it allows me to use gpt-4.1 and gpt-4o for free which is cool for simple stuff like engineering and migrations. I'm testing it locally currently. I now also made an account at Antropic to use that as well in case I need it. I have a local docker environment with php, mysql and apache running in a container. Claude had to adapt the pw-at.sh script quite a bit to make it work. I have no clue about this stuff, but it's working now. Thanks very much for the AgentTools module.

A few tweaks and a major improvement to the d() and db() calls from the Console panel - these now make use of Tracy's Lazy loading option so the DOM is not populated with huge nested objects - it gets generated dynamically as you toggle open each element with the object. This should solve the massive browser slowdown I am sure we've all experienced at times when dumping lots of large objects. This together with the change from localStorage to IndexedDB has made a huge improvement to the Console panel.

Hi everyone, Here in an updated version of the module It is now called NativeAnalytics. This should be treated as a **new module release**, not just a small update of the earlier test versions. "Important:" if you previously tested "PW Native Analytics", please **uninstall the old module first** and then install "NativeAnalytics" as a fresh install. I did "not" add a migration path from the old module to the new one, because the module name and structure changed during development. A clean install is the safer option. The main idea behind the module is simple: to provide a useful analytics dashboard directly inside ProcessWire, without relying on external analytics platforms, third-party scripts, or external APIs. Everything is handled natively inside the CMS, which makes it a good fit for projects where you want a simpler, more self-contained analytics solution. The module currently tracks and displays things like: page views unique visitors sessions current visitors top pages referrers devices and browsers 404 hits engagement events such as form submits, downloads, tel/mail clicks, outbound clicks, and custom CTA events It also includes: charts and trend views comparison between periods custom date range filtering page-level analytics inside the page edit screen exports to CSV, PDF, and DOCX helper examples and a small snippet generator for custom event tracking The reason I built it was that I wanted something that feels natural inside ProcessWire itself, instead of just embedding another analytics service into the admin. For many sites, it can be useful to have core traffic and engagement data available right where content is managed, with no need for external integrations. If you want, I can also make you a slightly shorter and more forum-friendly version with a stronger opening line like “Please uninstall the old PW Native Analytics test version before installing NativeAnalytics.” Download it Here: NativeAnalytics_1_0_8.zip Enjoy!

Hey everyone. I have a new Module in the works. It's 99.9% 75% ready for general release, but already running on my own sites for weeks. [Edit: see post about bug re. 3rd party module] If you've ever opened /site/templates/ on a project that's been running for a year, you know the feeling. 20-50 PHP with no structure, no grouping - an alphabetical avalanche. I usually get so far by namespacing all my files, but sometimes I wish for more organisation. Stemplates lets you organise your templates into folders. That's real directories on the filesystem - the way you're used to working. So, instead of leaving everything in a flat directory, you can go from this… site/templates/ ├── account-dashboard.php ├── account-billing.php ├── shipping-methods.php ├── shipping-tracking.php ├── blog-index.php ├── blog-post.php └── blog-category.php to this… site/templates/ ├── account/ │ ├── dashboard.php │ └── billing.php ├── shipping/ │ ├── methods.php │ ├── tracking.php └── blog/ ├── index.php ├── post.php └── category.php I've been running it on my own sites without issues for a while, and it takes just minutes to set up, even on a large site. Setup takes even less time if you're using AI/MCP. Even better, Stemplates is: ✅ completely non-destructive ✅ doesn't touch your database ✅ doesn't modify your templates or fields ✅ doesn't change anything in the admin UI ✅ doesn't alter your workflow ✅ free from manual aliases, no mapping files, no rewrite rules to maintain ✅ doesn't touch system templates (admin, repeaters, etc.) It also works with page classes and supports nested subfolders (50 levels tested). Understandably, I was reluctant to mess around with such a fundamental part of my sites, so a few safeguards exist... Migrate one template at a time at your own pace - no big switchover required Your existing flat templates keep working untouched, alongside any you've already moved If a file can't be found in its subfolder, ProcessWire falls back to its normal flat-folder behaviour automatically - the site doesn't break Uninstall cleanly at any time. Stemplates Free is undergoing a slight rework available now DM me for access. Stemplates Pro (coming soon) takes Stemplates even further. More soon, but honestly, Stemplates (Free) will take care of 99% of your new template -> folders world. Thanks for reading! Peter

Hey everyone! I'd like to share Start - a module that replaces the default ProcessWire admin home screen with a configurable personal dashboard. The problem it solves As your ProcessWire install grows, the Setup menu gets long - on smaller screens it overflows and you end up scrolling just to reach the tools you use every day. Start is the fix: think of it as the Windows Start button for your PW admin. Pin exactly what you need - modules, pages, whatever - and get to it in one click from the home screen. The result Features Two view modes - list and icon grid, preference saved per-browser Visual drag-and-drop editor at /setup/start/edit/ - reorder groups and links without page reloads Font Awesome 6 icons - 1887 icons with a searchable popup picker PagePicker - browse the full page tree directly from the URL field Example button - auto-populates with your installed Process modules and their FA icons Widget on the default admin home page Access control via start-dashboard permission Fully translated editor UI — 20 languages including RTL support for Hebrew and Arabic Supported languages English, Russian, German, French, Spanish, Polish, Ukrainian, Italian, Dutch, Portuguese, Chinese, Japanese, Turkish, Czech, Finnish, Korean, Hindi, Hebrew, Arabic, Hungarian. Installation Install like any other module — upload or place in /site/modules/, then install via Modules → Refresh. A Start item will appear under Setup in the admin menu. Make Start your admin home screen (optional) By default Start lives under Setup. To make it open whenever you click the admin logo or navigate to /admin/: Go to Pages in the admin menu Find the Admin page and click Edit In the Process field, select Start from the dropdown Save Links GitHub: https://github.com/mxmsmnv/Start

I have googled and ai-ed about it... We can call that a breaking change or not to our liking. Or holywar about it) My point was if someone downloads the new code to a site with PHP 7 the site will actually break 😎 But 2.0 is better anyway for marketing purpose and community spirit IMHO as it symbolizes the new era for the module)

This looks great @psy. Going to try it out later this week.

Sooo, I'm still alive and in August, I will start on a new job and project that probably brings me back to work with the cool and great Processwire. :D 7 years ago I was forced to change job and ended in a cool new place doing front-end dev not using PW anymore. So unfortunately I didn't really use or follow PW in that time except once a year doing something tiny bits on the handful of websites I am responsible for. I'm sorry if I just disappeared "over night" and maybe left some things behind I was doing for PW, and didn't spend time looking out for them. The reason is, I also was very frustrated with a lot of things with the job and life at that time and 2019 was also when I started painting again digitally, as maybe some of you know. I went full hyper focus mode, everyday almost for 2-3 years in my spare time and since then slowed down. I was able to make a small career with it, and made a lot of new connections and experiences which was awesome. I will continue to work on making art and illustrations as I have a lot of new freedom with the new job too combine a lot of my skills. Finally I can work from home full time. A little dream come true. Thanks for still being here and keeping this small but awesome community alive! I have to catch up now! :D Cheers Soma

Ryan did a nice blog post about this a few months back - https://processwire.com/blog/posts/api-variable-best-practices/

PromptWire 1.7.0 is out with 4 new MCP tools, bringing the total to 40. Latest tools are listed below. I haven't 100% fully tested a site sync yet, so always back up your existing site, database and files. pw_site_compare compares your local and remote sites across pages, schema, and template/module files. Pages are matched by URL path rather than database ID, so it works reliably across environments with different auto-increment sequences. You can exclude templates (e.g. user, role, licence pages) to focus the diff on what you actually intend to deploy. pw_site_sync (my favourite) orchestrates a full deployment in one operation: compare, back up the target, enable maintenance mode, push schema, push pages with their file/image assets, push template and module files, disable maintenance. It runs in dry-run mode by default so you see the full plan before anything is touched. Scope can be narrowed to just pages, schema, or files. pw_maintenance toggles maintenance mode on local, remote, or both sites. A styled 503 page is served to visitors with appropriate Retry-After and noindex headers. Superusers and the PromptWire API bypass it, so you can verify changes and keep the agent working during a deployment. pw_backup creates database dumps (using ProcessWire's WireDatabaseBackup) and zip archives of site/templates and site/modules. You can list, restore, or delete backups from either environment. The backup directory is auto-protected with .htaccess so SQL dumps are never web-accessible. HTTPS enforcement. The API endpoint rejects plain HTTP with a 403 before the API key is checked. PROMPTWIRE_ALLOW_HTTP in config-promptwire.php bypasses this for local dev only. Autoload change. The module is now autoloaded to intercept front-end requests during maintenance mode. The cost is a single file_exists() check per page load. Documentation updated across all pages at peterknight.digital/docs/promptwire/v1/

I tried integrating Columns, but it had issues with drag-and-drop blocks. So I released the beta version without it. The most important thing now is the stability of the beta version so we can move on to adding other features. Roadmap: Dark theme - there is a bug now, you need to change the reverse colors Localizing text in the editor so that it looks native on websites with a different language set in the admin panel Multilingual support - for example, for websites from Switzerland and Belgium, this is more relevant. Gallery (Slider) - the ability to upload multiple photos at once Textformatter support to allow connection to other text processors Columns plugin for adding column view If you know what works poorly or doesn't work at all, and would like to add something, I'd be happy to hear your suggestions!

@AndZyk OpenRouter is already supported. Here's how you'd configure it in the AgentTools module configuration (as an example): google/gemini-2.0-flash | sk-or-YOUR_KEY | https://openrouter.ai/api/v1 | Gemini via OpenRouter anthropic/claude-sonnet-4-6 | sk-or-YOUR_KEY | https://openrouter.ai/api/v1 | Claude via OpenRouter @HMCB Thanks! 🙂

@ryan this is beyond amazing. It’s hard to put into words. Thank you!

Very interesting module, thank you @ryan. 🙂 Would it be possible to support API keys from OpenRouter? We use OpenRouter to switch between many models. Regards, Andreas

Btw, one feature that wasn't quite ready this week for AgentTools was Engineer memory. Currently every prompt is like a new thread. But next week we'll enable memory, so that it has context of all your previous prompts.

😂 https://www.tomshardware.com/tech-industry/artificial-intelligence/claude-code-deletes-developers-production-setup-including-its-database-and-snapshots-2-5-years-of-records-were-nuked-in-an-instant EDIT, the post-mortem by the developer: https://alexeyondata.substack.com/p/how-i-dropped-our-production-database

Enables AI coding agents to access ProcessWire’s API. Also provides a content migration system. This module provides a way for Claude Code (or other AI helpers) to have full access to the ProcessWire API via a command-line interface (CLI). Once connected to your site, you can ask Claude to create and modify pages, templates and fields, or do anything that can be done with the ProcessWire API. It's even possible for an entire site to be managed by Claude without the need for ProcessWire's admin control panel, though we're not suggesting that just yet. While working with Claude Code, I asked what would be helpful for them in working with ProcessWire, and this module is the result. Claude needed a way to quickly access the ProcessWire API from the command line, and this module provides 3 distinct ways for Claude to do so. Claude collaborated with me on the development of the AgentTools module, and the accompanying ProcessAgentTools module was developed entirely by Claude Code. Admittedly, a big part of the purpose of this module is also to help me learn AI-assisted development, as I'm still quite new to it, but learning quickly. This module aims to add several agent tools over time, but this first version is also somewhat of a proof of concept. Its first feature is basic migrations system, described further in this document. Please note that this module should be considered very much in 'beta test' at this stage. If you do use it in production (such as the migrations feature) always test locally and have backups of everything that can be restored easily. While I've not run into any cases where I had to restore anything, just the nature of the module means that you should use extra caution. Continue reading in the GitHub README Agent Tools in the modules directory

If you love the simplicity of ProcessWire's API but want the reactive, SPA-like feel of modern frontend frameworks without writing complex JavaScript, this module bridges that gap. It brings native Server-Side Component state hydration, Out-Of-Band (OOB) swaps, and strict security to your ProcessWire application using HTMX. 🚀 What does it do? This module transforms how you write frontend components in ProcessWire: True Stateful Backend Components: It introduces Component and Ui base classes. Your PHP components automatically rehydrate their state (variables, dependencies, $page assignments) between HTMX AJAX requests! No need to manually parse POST payloads. Auto-Discovery: Just place your components in your site directories. The module automatically discovers and securely namespaces them (Htmx\Component and Htmx\Ui). Zero-Javascript Reactivity: You can handle form submissions, counters, validation, and multi-field updating dependencies directly from PHP using HTMX attributes. Cryptographic Security: The module uses strict HMAC-SHA256 signatures with TTL (Time-To-Live). This guarantees that bad actors cannot modify state payloads or trigger invalid endpoint logic in the browser. WebSockets & SSE Ready: It has built-in helpers to easily hook Server-Sent Events (SSE) and WebSockets onto your templates without exhausting PHP-FPM pools globally. 🛠 How it looks in your code You simply create a PHP component class, define some public properties, and write an endpoint action: <?php namespace Htmx\Component; use Totoglu\Htmx\Component; class ClickCounter extends Component { public int $count = 0; public function increase() { $this->count++; } } Then, you can render it anywhere in your site with a single line: /** @var Htmx $htmx */ echo $htmx->renderComponent(ClickCounter::class); View the documentation and examples on Github Feel free to try it out, run the tests included in the repo, and let me know your thoughts or feedback! htmx.mp4

I'm not trying to self promote, but the store is finished. It's outside of processwire, but the rest of the site is all PW. It would be nice to tie it all together. Now that I have it working, I think I could do that, but that's another project for some time when I have nothing else to do. https://www.sonrisestable.com/store/