Version 4.3

EZGPT.APP

Chat with your own models, in your browser or on your Android phone.

EZGPT.APP is a chat window for your own language models: a side panel in Chrome and Edge, and an app for Android phones and tablets. Point it at LM Studio or Ollama on your PC, a server on your LAN, or a cloud service with your own key. Ask one model, or put two to four on a panel and keep the answer they vote for. Nothing goes anywhere except the server you configured.

Add to Chrome · Free Get it on Google Play

Extension: free, Chrome and Edge 116 or newer. Android: USD 1.99 on Google Play. No EZGPT.APP account. See the setup

The EZGPT.APP side panel, showing a prompt, a collapsed reasoning block and an answer, with the composer below. The same chat in the EZGPT.APP Android app
Android · on Google Play

EZGPT.APP on your phone

The EZGPT.APP chat on your phone or tablet. Point it at LM Studio or Ollama on your PC over your own Wi-Fi, or at a cloud service with your own key.

Comes along

  • Group chat, with debate and voting
  • Reasoning blocks, images, and Markdown with code copy
  • Prompt snippets and per-chat parameters
  • Chat history, with export and backup through the share sheet
  • Keyboard shortcuts, with a hardware keyboard
  • On tablets, the chat list beside the conversation

Stays in the browser

  • The side panel and its Ctrl+Shift+E shortcut
  • Attach page and the right-click menu
  • Open in tab

There is no EZGPT.APP account and no server of ours; chats and settings stay on the phone. LM Studio and Ollama need no account at all. A cloud service such as ChatGPT or Claude needs your own account and API key with that service.

USD 1.99, once, on Google Play, bought with your Google account. No subscription and nothing to buy inside. Google shows the price in your own currency.

Get it on Google Play
A chat with a reasoning block and a code block, on a phone A group chat on a phone: the winner, then every model's answer Settings on a phone with the cloud services strip

Report a problem or ask a question

What's new in 4.3

Group chat. Pick two to four models and ask once. Every model answers, reads the others, revises, then votes. The answer with the most votes is the reply, and the whole debate is one tap away.
Cloud services one tap away. ChatGPT, Claude, Grok, Gemini, DeepSeek, Mistral, Groq and OpenRouter, each with a link to its API key page. Local servers work as before.
Debate rounds you control. A slider up to five rounds. The panel stops early as soon as no model changes its answer, so five rarely costs five.
A refreshed look. A lit command line for your message, a quieter transcript and larger controls that work under a thumb.
Models tagged mid-conversation. When you switch models partway through a chat, the reply shows which model wrote it, and a provider's new default model takes effect at once.
Now on Android. The chat in a phone-sized window, talking to the servers on your network or to a cloud service with your key. A one-time purchase on Google Play.

Works with

LM Studio

On localhost or your LAN. The default preset.

Local

Ollama

On localhost or your LAN. No extra CORS setup needed.

Local

OpenAI

Through the chat completions API with your own key.

Cloud

OpenRouter

Hundreds of hosted models behind one key.

Cloud

Anthropic

Claude models through the OpenAI-compatible endpoint.

Cloud

Gemini

Google models through the OpenAI-compatible endpoint.

Cloud

Grok (xAI)

Preset for api.x.ai with your xAI key.

Cloud

DeepSeek

Preset for api.deepseek.com with your DeepSeek key.

Cloud

Mistral

Preset for api.mistral.ai with your Mistral key.

Cloud

Groq

Preset for Groq's OpenAI-compatible endpoint with your Groq key.

Cloud

Any OpenAI-compatible server

vLLM, llama.cpp, LocalAI, text-generation-webui and others.

Custom

What you get

🗳️

Group chat

Two to four models answer the same question, debate, then vote. You read the winner; the debate is one tap away.

☁️

Cloud services with one tap

ChatGPT, Claude, Grok, Gemini, DeepSeek, Mistral, Groq and OpenRouter presets, with a link to each key page.

🧭

Side panel first

Open it with one click or Ctrl+Shift+E. It stays open while you browse, and the reply keeps streaming.

🔀

Model switcher in the top bar

Discover the models a server offers and change model per chat without editing settings.

⏹️

Streaming with a Stop button

Partial replies are kept if you stop or close the panel.

🧠

Reasoning models handled

DeepSeek, Qwen, QwQ and gpt-oss style thinking shows in a collapsible block, whether the server sends it as a reasoning field or as think tags.

📄

Ask about the page

Attach the selected text or the readable text of the current tab to your message. Right-click any selection and choose "Ask EZGPT.APP about…".

🖼️

Images

Paste, drop or attach screenshots for vision models such as Qwen-VL, LLaVA, Pixtral or GPT-4o.

📝

Markdown answers

Code blocks with one-click copy.

🎛️

Per-chat parameters

Temperature, top-p, max tokens and stop sequences, set for each chat.

✂️

Prompt snippets

Save the prompts you reuse from the composer's tool row and insert them with a click.

🗂️

History you own

Search, rename and grouping by day. Export a chat as Markdown or JSON, or back up everything as one file and restore it later.

🎨

Your look

Light, dark and system themes, four accents, three densities.

🪟

Full tab when you want room

Click "Open in tab" in the top bar to get the same chat in a full tab, with the chat list as a permanent left column.

See it

Streamed markdown reply with a code block in the side panel
Group chat: three models answer, debate and vote, the winner on top
Collapsible reasoning block and the model switcher
Settings with one-tap cloud services: ChatGPT, Claude, Grok, Gemini, DeepSeek, Mistral, Groq, OpenRouter
Page context chip attached to a message
Provider settings with presets for LM Studio, Ollama, OpenAI and OpenRouter
Full tab mode with the chat history sidebar

Get EZGPT.APP

Browser extension · Free

Chrome and Edge

The side panel, plus Attach page, the right-click menu and Open in tab. One click from the Chrome Web Store, for Chrome and Edge 116 or newer.

  • One-click installation
  • Automatic updates
  • 3.x settings migrate automatically

Free • Version 4.3

Android app · USD 1.99

Android phones and tablets

Group chat, cloud services and your local servers on your phone, with a tablet layout that keeps the chat list beside the conversation. A one-time purchase: no subscription and nothing to buy inside.

  • Updates through Google Play
  • Export and backup through the share sheet
  • Google shows the price in your own currency
Get it on Google Play

USD 1.99 once • Bought with your Google account

Neither needs an EZGPT.APP account. LM Studio and Ollama need no account at all; a cloud service needs your own account and API key with that service.

Getting started

Start your model server, click the EZGPT.APP icon, pick a model in the top bar and type your first message. Pick your server below for the details.

LM Studio

  1. Install LM Studio and load a model.
  2. In LM Studio go to Developer → Start server. It listens on port 1234 by default.
  3. Click the EZGPT.APP icon. The side panel opens with the LM Studio preset at http://localhost:1234/v1 already selected.
  4. The first time, the browser asks to allow access to localhost:1234. Allow it.
  5. Pick a model from the model dropdown in the top bar and type your first message.
Preset: LM Studio
Server URL: http://localhost:1234/v1
API key: (leave empty)
Model: model dropdown in the top bar

Running LM Studio on another machine on your LAN? Use its IP instead of localhost and tick "Serve on local network" in LM Studio.

Ollama

  1. Install Ollama and pull a model, for example ollama pull llama3.2. Ollama's server is already running once it is installed.
  2. Click the EZGPT.APP icon, open Settings → Providers and click Add provider. Choose the Ollama preset, which fills in http://localhost:11434/v1, then Save provider.
  3. On save, the browser asks to allow access to localhost:11434. Allow it. You do not need to set OLLAMA_ORIGINS.
  4. Pick Ollama in the top-bar provider dropdown, or click Use on its card. Pick a model from the model dropdown and type your first message.
Preset: Ollama
Server URL: http://localhost:11434/v1
API key: (leave empty)
Model: model dropdown in the top bar

Cloud services

  1. Open Settings → Providers.
  2. Tap the service under Add a cloud service: ChatGPT, Claude, Grok, Gemini, DeepSeek, Mistral, Groq or OpenRouter.
  3. The form opens with the address filled in and a Get a key link. Paste the key, press Discover models (or type a model name if the service does not list them), Save.
  4. Pick the model in the top bar and ask.

Each service bills your own account. EZGPT.APP never sees the key except to send it to that service.

OpenRouter, Anthropic and Gemini

These cloud services are reached through their OpenAI-compatible endpoints. Each has a preset, so you only add a key.

  1. Get a key from the service: OpenRouter, Anthropic or Google AI Studio for Gemini.
  2. In EZGPT.APP open Settings → Providers, click Add provider and choose the OpenRouter, Anthropic or Gemini preset. The base URL is filled in for you.
  3. Paste your key, click Discover models, then Save provider. Allow access to that service's address when the browser asks.
  4. Pick the provider in the top-bar dropdown, then pick a model from the model dropdown. OpenRouter lists every model your key can reach.
Preset: OpenRouter · Anthropic · Gemini
Server URL: filled in by the preset
API key: your key for that service
Model: model dropdown in the top bar

Use Alt+1…9 to jump between the providers you have set up.

Any OpenAI-compatible server

EZGPT.APP works with any server that speaks the OpenAI chat completions API: vLLM, llama.cpp, LocalAI, text-generation-webui and others, on your machine, your LAN or a host you rent.

  1. In EZGPT.APP open Settings → Providers, click Add provider and choose the Custom preset.
  2. Enter the server's base URL, usually ending in /v1, and a key if the server needs one.
  3. Click Test connection and Discover models, then Save provider. Allow access to that address when the browser asks.
  4. Pick the provider in the top-bar dropdown, then pick a model from the model dropdown.
Preset: Custom
Server URL: http://your-host:port/v1
API key: (if the server requires one)
Model: model dropdown in the top bar

Group chat

  1. Open the chat list and tap New group chat.
  2. Tick two to four models, from any providers you have.
  3. Set the debate rounds, zero to five. The panel ends the debate early once nobody changes their answer.
  4. Tap Use this panel and ask your question. Every model answers, then they read each other, revise and vote. The winner is the reply; open Debate and votes to read the rest.

Keyboard shortcuts

Ctrl+Shift+EOpen the side panel
EnterSend
Shift+EnterNew line
EscStop
Ctrl+NNew chat
Ctrl+KSearch chats
Ctrl+Shift+PAttach page
Ctrl+,Settings
Alt+1…9Switch provider

Privacy

🚫

No EZGPT.APP account, no analytics, no telemetry

There is no server on our side. The extension contains no analytics library, no crash reporter, no advertising and no remote code. Cloud services you add have their own accounts, billing and privacy policies.

💾

Everything stays on your device

Settings, chats and images live in your browser's storage, or in the Android app. Uninstalling deletes them.

🔌

Talks only to your servers

Requests go only to the servers you add, and only when you send a message, discover models or test a connection. The Android app works the same way.

👆

Page text only on click

Page text is read only when you click "Attach page" or use the context menu. Never in the background.

Read the full privacy policy

Upgrading from 3.x

Your providers, chats, images and snippets are migrated automatically the first time 4.0 starts. The popup and detached window are replaced by the side panel. Open it with the toolbar icon or Ctrl+Shift+E. The first time you talk to each server, the browser asks you to allow access to that address. 3.x asked for every website at install; 4.0 asks for nothing until you use something.

Download EZGPT.APP

Ready to get started?

Add EZGPT.APP to your browser, or get it for your Android phone, and chat with your own models.

✅ Local, LAN or cloud models
✅ Any OpenAI-compatible API
✅ Nothing leaves your device but your own requests
✅ Ready in under a minute
Get it on Google Play

Extension free • Android USD 1.99 • No EZGPT.APP account