AnyLLM App User Guide and Support

USER GUIDE & SUPPORT

Last updated February 9, 2025

This guide explains how to use the AnyLLM application ("App") and where to get help. AnyLLM lets you chat with AI models using the provider you choose—Cloud Models, Ollama, or LM Studio—while keeping your conversations and settings on your device.

1. WHAT IS ANYLLM?

In Short: AnyLLM is a chat application that connects you to AI models through the provider you configure. Your conversations and settings stay on your device; we do not collect or store your chats on our servers.

AnyLLM is a mobile and desktop application that allows you to send prompts and receive responses from large language models (LLMs). Unlike many chat apps, AnyLLM does not require an account with us. You can use:

• Cloud Models — use a wide range of models over the internet; access is configured automatically by the App.

• Ollama — run models locally on your computer; you install and manage Ollama separately.

• LM Studio — run models locally using LM Studio on your computer; you install and manage LM Studio separately.

Your conversation history and settings are stored locally on your device. Cloud Models access is configured automatically by the App; we do not collect or store your chats on our servers. For more detail, see our Privacy Notice.

2. GETTING STARTED

In Short: Install the App from your app store or distribution channel, open it, then configure at least one AI provider and select a model before chatting.

• Install the App. Download and install AnyLLM from the Apple App Store, Google Play, or other official distribution channel you use.

• Open the App. On first launch, you will see the chat screen. You need to set up at least one AI provider and choose a model before you can send messages.

• Configure an AI provider. Cloud Models access is configured automatically by the App. For local providers, go to Settings and set up Ollama (URL of your Ollama server) and/or LM Studio (URL of your LM Studio server). Save or update the URL and confirm connection where the App offers it.

• Select a model. Open the menu (e.g. swipe from the left or tap the menu icon), then choose "Select Model." Pick the provider and the specific model you want to use. You can change the model at any time.

• Start chatting. Once a model is selected, type your message in the input area and send. Responses appear in the conversation. You can start a new chat or switch between past chats from the menu.

3. CHOOSING AN AI PROVIDER

In Short: You can use Cloud Models, Ollama (local), or LM Studio (local). Cloud Models access is configured automatically; for Ollama and LM Studio you set the server URL in Settings. You choose which one to use via "Select Model."

Cloud Models 

• Cloud Models give you access to many AI models over the internet. Access is configured automatically by the App.

• In Settings, find the Cloud Models / AI Model Setup section to browse and select models. Your prompts and the model's responses are sent to the cloud provider; their privacy policy and terms apply to that data.

Ollama (local)

• Ollama runs models on your own machine. You must install and run Ollama separately (see ollama.ai). The App connects to your Ollama server.

• In Settings, under the Ollama section, enter the Ollama URL (e.g. http://localhost:11434 for the same device). Tap "Update URL" and check the connection status. If connected, available models appear; pull models in Ollama if needed.

• Select an Ollama model via "Select Model" in the menu. Your prompts and responses stay between your device and your Ollama server; we do not receive them.

LM Studio (local)

• LM Studio lets you run models locally on your computer. You must install and run LM Studio separately and start the local server. The App connects to that server.

• In Settings, under the LM Studio section, enter the LM Studio server URL (e.g. http://localhost:1234). Update the URL and check the connection. If connected, you can choose a model from the list.

• Select an LM Studio model via "Select Model." Your prompts and responses stay between your device and your LM Studio server; we do not receive them.

Switching providers

• You can switch between Cloud Models, Ollama, and LM Studio at any time using "Select Model" from the menu. The currently selected provider and model are used for new messages in the current chat until you change them.

4. SETTINGS OVERVIEW

In Short: Settings are available from the menu or app bar. They cover theme, voice/TTS, fonts, and AI provider setup (Cloud Models, Ollama, LM Studio).

How to open Settings

• Open the main menu (e.g. swipe from the left edge or tap the menu icon), then tap "More Settings," or use the settings entry point from the app bar if available. This opens the full Settings screen.

General settings

• App theme: Choose System (follow device), Light, or Dark.

Voice settings

• Auto Speak Responses: When enabled, the App can read responses aloud as they are generated (text-to-speech). You can turn this on or off in Settings.

• Auto-Detect "Send" Command: When using voice input, you can optionally have the App send the message when you say "Send." Enable or disable this in Settings.

• Silence Timer Auto Send: For voice input, you can automatically send the message after a period of silence. Enable this and set the delay (e.g. 1–10 seconds) in Settings.

• TTS Engine: Choose between "System TTS" (your device's built-in text-to-speech) and "InApp Speech" (on-device speech engine). InApp Speech may offer additional voices and controls.

• Speaker Voice (InApp Speech): If you use InApp Speech, you can select the speaker/voice in Settings.

• Speech Speed: Adjust how fast the voice speaks (e.g. 0.5x to 3x) in Settings.

Font settings

• Font style and size can be adjusted in Settings. A preview shows how text will look. These apply to how messages are displayed in the App.

AI model setup (Settings)

• Cloud Models: Access is configured automatically by the App. Use the model browser or list in Settings to add and select models.

• Ollama: Enter the Ollama server URL, tap "Update URL," and check connection. Select from available Ollama models in Settings or via "Select Model."

• LM Studio: Enter the LM Studio server URL, update, and check connection. Select from available LM Studio models in Settings or via "Select Model."

Settings are stored on your device. We do not have access to them.

5. USING THE CHAT

In Short: Type or speak your message, send it, and read or listen to the response. You can start a new chat, clear the current chat, or open past chats from the menu.

Sending messages

• Type your message in the text field at the bottom and send (e.g. tap the send button or use the keyboard shortcut). If you have not selected a model, the App may prompt you to choose one first.

• Voice input: Use the microphone button to speak. Your speech is converted to text and placed in the input field. You can edit before sending. If "Auto-Detect Send Command" or "Silence Timer Auto Send" is on, the message may be sent automatically as described in Settings.

• You can attach or paste content (e.g. images) where the App supports it; follow the in-app prompts. Sending media may depend on the model and provider you use.

Receiving responses

• The AI model's reply appears in the conversation. If "Auto Speak Responses" is on, the App can read the response aloud. You can usually tap a message to speak it again or stop speaking.

• Generation may take a few seconds or longer depending on the model and your connection. You can typically stop generation with an on-screen control if the App offers it.

New chat and clear chat

• New chat: Open the menu and tap "New Chat." This starts a fresh conversation. Your previous chats remain in chat history unless you delete them or clear data.

• Clear chat: Open the menu and tap "Clear Chat." You will be asked to confirm. This clears the current conversation only; it does not delete other chats or settings.

Chat history

• Past chats appear in the menu (e.g. under "CHAT HISTORY"). Tap a chat to open it. All history is stored on your device; we do not have access to it.

6. VOICE AND TEXT-TO-SPEECH

In Short: You can speak your messages (voice input) and have responses read aloud (text-to-speech). Configure both in Settings.

Voice input (speech-to-text)

• Use the microphone button to start voice input. Speak; your words appear as text. You can then edit and send. Permissions (e.g. microphone) may be required on your device.

• Optional: Enable "Auto-Detect Send Command" to send when you say "Send," or "Silence Timer Auto Send" to send after a period of silence. Adjust these in Settings.

Text-to-speech (TTS)

• Enable "Auto Speak Responses" in Settings to have the App read responses as they are generated (or when complete, depending on implementation).

• Choose "System TTS" (device voice) or "InApp Speech" (on-device engine). With InApp Speech, you can pick a speaker and speech speed. TTS runs on your device or uses system APIs; we do not receive your conversation content.

7. CHAT HISTORY AND DATA

In Short: Your chats and settings are stored only on your device. You can delete a chat, clear the current chat, or clear all App data via your device or OS settings.

• Where data is stored: Conversation history and app settings are kept locally on your device. Cloud Models access is configured automatically by the App. We do not collect or store this data on our servers.

• Deleting or clearing: Use "Clear Chat" in the menu to clear the current conversation. To remove all App data (including all chats and settings), use your device's application management: clear data for AnyLLM or uninstall the App. We do not retain copies once you clear or uninstall.

• Third-party providers: If you use Cloud Models, Ollama, or LM Studio, their own policies apply to any data they receive. We do not control their retention or use of that data.

8. TROUBLESHOOTING

In Short: Most issues are due to provider setup (URL or model). Cloud Models access is configured automatically; for local providers, check the URL and connection in Settings.

"No model selected" or cannot send messages

• Make sure you have chosen a model: Open the menu → "Select Model" → pick a provider and a model.

• For Cloud Models: Access is configured automatically. Check that the model you selected is available and that your device has internet access.

• For Ollama: In Settings, check the Ollama URL (e.g. http://localhost:11434). Tap "Update URL" and use the refresh/connection check. Ensure Ollama is running on that machine and that you have pulled at least one model (e.g. via Ollama CLI or app).

• For LM Studio: In Settings, check the LM Studio server URL (e.g. http://localhost:1234). Ensure LM Studio is running and the local server is started. Load a model in LM Studio if needed.

Connection or network errors

• For Cloud Models: Verify your device has internet access. Access is configured automatically by the App; if requests fail, check the cloud provider's status or documentation.

• For local (Ollama / LM Studio): If the App and the server are on different devices, use the correct IP and port (e.g. http://192.168.x.x:11434 for Ollama). Ensure firewall or network settings allow the connection.

Voice or TTS not working

• Grant microphone permission for voice input if the App requests it. Check device settings → Apps → AnyLLM → Permissions.

• For TTS: If "Auto Speak Responses" is on and nothing plays, try selecting "System TTS" in Settings, or check device volume and "Do Not Disturb" settings. For InApp Speech, ensure the chosen voice is available and speech speed is not set to an extreme.

App crashes or behaves oddly

• Restart the App. If the issue continues, try clearing the App cache or data (note: clearing data removes all chats and settings). Ensure you are on a supported OS version and that you have the latest App update from your store.

• If the problem persists, contact us with your device model, OS version, App version, and a short description of what happens. We do not have access to your chats, so please do not send sensitive content; describe the steps and error only.

9. CONTACT AND SUPPORT

In Short: For questions, feedback, or technical support, email us at 2asoftwaredevelopers@gmail.com. You can also use "Contact Us" from within the App if available.

• Email: 2asoftwaredevelopers@gmail.com

• Use for: How-to questions, bug reports, feature requests, or account/legal inquiries. We do our best to respond in a reasonable time but do not guarantee a specific response time.

• When contacting support: Please include your device type, OS version, and App version (e.g. from the menu or About screen). For connection or provider issues, describe which provider you use (Cloud Models, Ollama, LM Studio) and what you see (e.g. "Not connected," error message). Do not send full conversation content; we do not need and should not receive it for support.

10. PRIVACY AND TERMS

In Short: Your use of AnyLLM is subject to our Privacy Notice and Terms and Conditions of Use. We do not collect your conversations or usage data from the App.

• Privacy Notice: Describes what information we do and do not collect, how we use it, and your rights. We do not collect your chats or prompts from the App; they stay on your device. Cloud Models access is configured automatically by the App.

• Terms and Conditions of Use: Set the rules for using our Services, including acceptable use, disclaimers, and limitation of liability. By using the App, you agree to those terms.

• Links: Where the App or our distribution channels provide links to the Privacy Notice and Terms, please read them. If you have questions about privacy or terms, contact us at 2asoftwaredevelopers@gmail.com.

Thank you for using AnyLLM. We hope this guide helps you get the most out of the App. For the latest version of this guide, check the in-app help or the source where you downloaded the App.