Ptero: A Free, Open-Source Multi-Model AI Chat Platform for the Web and WordPress
AI Chat with powerful models for free
At a glance
- What is it?
- Ptero is a free, open-source AI chat platform that provides access to multiple large language models through a single browser interface, with no account required and all conversation history stored locally in the browser. A WordPress plugin version embeds the full chat interface on any page via a shortcode.
- Who is it for?
- Developers, students, and content creators who want to compare multiple AI model outputs without signing up for paid services or creating accounts will find Ptero useful at ptero.pro. WordPress site owners who want to embed an AI chat interface can use the companion Pterocos plugin with the [mlp_ai_chat] shortcode.
- Can I use it commercially?
- Yes. Apache-2.0 is a permissive licence: you can use, modify and sell software built on it, as long as you keep its copyright and licence notices.
- Is it still maintained?
- Yes. The repository last received commits 2 days ago.
- What is it written in?
- Mainly PHP, according to GitHub's language statistics.
Answers come from the project's GitHub data, last synced on September 29, 2026, and from our analysis. They are not legal advice.
Editorial analysis
What Ptero Provides and Who It Is For
Ptero is described in the README as a non-profit project that provides access to multiple large language models through a single interface at no cost. The platform runs at ptero.pro and requires no account creation, no payment method, and no subscription. A display name is saved locally on the user's device and is the only persistent identity the application maintains.
The README explicitly states that Ptero does not offer paid plans or subscriptions and that access to all models is provided at no cost. The target audience described in the README is developers, students, and creators who value privacy and simplicity over the account-based model of mainstream AI services.
The project is open-source and self-hostable. The repository contains the PHP backend for WordPress integration and the JavaScript, HTML, and CSS frontend. The AI integrations connect to external model providers rather than running models locally.
The Model Roster and How Switching Works
The README lists the following models as available: DeepSeek V4, Llama 3.3, Qwen, MiniMax, Mistral, and more. The phrase "and more" appears in the README without further specifics. One-click model switching is described as a feature that lets users instantly switch between models to compare responses within the same conversation context.
The README mentions the project is supported by modelrunner.ai and minirouter as sponsor integrations, which suggests the model routing infrastructure depends on these third-party services rather than direct API calls to each provider. The README does not document which specific model providers are called, what rate limits apply, or what happens when a sponsored provider's capacity is reached.
Conversation organization is handled through a project-based workspace that groups conversations. A media library allows file uploads within chats to provide context for model queries.
Privacy Model: Browser-Local Storage
The README states directly that all conversations are stored locally in the user's browser and that no chat history is saved on Ptero's servers. This is presented as a deliberate design choice, not a limitation. For users in environments where conversation content is sensitive, the local-only storage means that clearing browser data deletes all conversation history permanently.
The corollary is that there is no synchronization across devices. A conversation started on a desktop browser is not available on a mobile browser, and conversation history does not follow a user who clears browser storage or switches to a private browsing window. The README does not document an export or backup mechanism for existing conversations.
The display name a user sets at first visit is also stored locally on the device. No account system means no recovery option if local data is lost.
Adding Ptero to a WordPress Site
The README documents a separate WordPress plugin called Pterocos, hosted at a different repository (github.com/aminkheddache-dotcom/Pterocos). Installing it follows standard WordPress plugin installation: download the plugin, upload and activate it in the WordPress admin, and then place the shortcode [mlp_ai_chat] on any page or post where the chat interface should appear.
The README does not document what the shortcode parameters are, whether the WordPress plugin shares the same local-storage privacy model as the standalone web version, or whether site visitors need any account to use the embedded chat. The technology stack section lists PHP as the backend language specifically for the WordPress integration and REST API, suggesting the WordPress plugin adds server-side handling not present in the standalone JavaScript frontend.
For non-WordPress sites, the README describes only the standalone web version at ptero.pro and does not document an embed or iframe approach for other platforms.
Where Ptero Is Not the Right Tool
Ptero stores no conversation history on its servers by design. Teams that need audit trails, conversation logging, or shared access to conversation history across users cannot use Ptero without building their own storage layer on top of it.
The free, no-account model depends on sponsor support. The README credits two sponsor organizations and lists modelrunner.ai and minirouter as infrastructure partners. This means service continuity depends on those sponsorships remaining in place, which is a risk not present with paid API access to model providers directly.
The README does not document API rate limits, maximum context lengths per model, or what happens to conversation context when switching between models mid-session. For developers building applications that require predictable behavior, the lack of documented SLAs and the dependency on third-party routing infrastructure make Ptero unsuitable as a backend component.
License and Source Code
The README states that Ptero is licensed under GPL v2 or later, with a note that this ensures the project remains free and open-source for everyone. The repository contains five top-level files: CODE_OF_CONDUCT.md, LICENSE, README.md, ai-logic.php, and ptero-ai-chat.php. The two PHP files handle the core AI logic and the main plugin entry point.
The last push to the main branch was on 2026-09-15. The repository has no GitHub releases and the README does not document a version number or changelog. The Apache-2.0 badge visible in the README's badge section conflicts with the GPL v2 statement in the License section; the LICENSE file and the README text both claim GPL v2, and the Apache badge appears to be a display artifact rather than a license indicator.
Contributions follow standard GitHub pull request flow. The README invites contributors to report issues, submit pull requests, and join the Discord community. Issues labeled good-first-issue are designated for newcomers as a starting point for code contributions.
Editorial conclusion
Developers, students, and content creators who want to compare multiple AI model outputs without signing up for paid services or creating accounts will find Ptero useful at ptero.pro. WordPress site owners who want to embed an AI chat interface can use the companion Pterocos plugin with the [mlp_ai_chat] shortcode. Teams that need conversation persistence across devices or server-side logging should note that Ptero explicitly stores no chat history on its servers; all conversation data lives in the user's browser only.
Frequently asked questions
What AI models does Ptero support?
The README lists DeepSeek V4, Llama 3.3, Qwen, MiniMax, and Mistral as available models, with a note that more models are accessible. One-click switching between models is a documented feature.
How does Ptero handle conversation privacy?
Ptero stores all conversation history locally in the user's browser only. The README explicitly states that no chat history is saved on the project's servers. Clearing browser data deletes all conversations permanently.
Can Ptero be embedded on a non-WordPress website?
The README documents a WordPress plugin called Pterocos for embedding via the [mlp_ai_chat] shortcode, but does not describe an embed approach for non-WordPress platforms. The standalone version at ptero.pro is the only documented path for non-WordPress users.
Official sources
Add this badge to your README
If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.
[](https://hysenlabs.com/projects/aminkheddache-dotcom-ptero)