Security, Privacy
& Terms

Everything you need to know about how InferencePort handles your data and what you agree to by using it.

Security & Privacy Policy

Last updated: 16 February 2026

Account Requirements

InferencePort AI does not require users to create an account. The application can be used without signing in. Signing in is optional and is only required if you choose to enable certain features such as chat syncing or server connecting.

Chat Data & Syncing

By default, all chats are stored locally on your device. When you are not signed in, no chat data is transmitted to or stored on our servers.

If you sign in and explicitly enable chat syncing, your chat messages and conversation metadata are collected and stored securely to synchronize your chats across devices.

  • Chat syncing is disabled by default
  • Chats are only collected when both signed in AND syncing is enabled
  • You may disable chat syncing at any time, but this may not delete existing data
  • To request deletion of your chats, email [email protected]
☁ Lightning / Cloud Models: Requests to InferencePort Lightning — including chat messages and sessions — may be processed on our or our vendors' servers. We aim for zero-data retention but cannot guarantee it. Please read the privacy policies of Pollinations.AI, Groq, and Cerebras AI before using cloud features.

Data Collected When Signing In

If you choose to create an account, we may collect:

  • Email address (for authentication and account recovery)
  • Name
  • Encrypted authentication credentials
  • Optional username (public-facing, not encrypted)
  • Other data collected by third-party authentication providers

Do not use personally identifying information in your username.

Third-Party Services

InferencePort AI does not use third-party analytics, advertising, or tracking services by default. The application may interact with:

Data transmitted to these services is always user-initiated. Some services may process data on servers outside the United States.

Security Practices

  • All code is reviewed and tested before release
  • Dependencies are regularly updated to address vulnerabilities
  • Sensitive data is encrypted where applicable
  • InferencePort is fully open source — independently auditable on GitHub

Contact

For security concerns, email [email protected] with subject line "InferencePort AI Security Disclosure".

⚠ Do not disclose security vulnerabilities on GitHub. Use the email above only.

For general questions, open a GitHub issue or email [email protected] with subject "InferencePort AI General Question". Reports are generally reviewed within 1–2 weeks.


Terms of Service

Last updated: 23 February 2026

These Terms of Service ("Terms") govern your use of InferencePort AI (the "Application"), developed by Rihaan Meher (the "Developer"). By installing, accessing, or using the Application, you agree to these Terms.

1. Nature of the Application

InferencePort AI is a desktop application that allows users to run locally installed generative AI models on their own devices. The Application does not require the Developer to operate servers for AI inference, and AI-generated content is produced entirely on the user's device (for local models).

The Developer does not control, monitor, review, filter, moderate, or store any AI-generated content produced by the Application, unless explicitly shared using report methods or the chat sync feature.

2. AI-Generated Content Disclaimer

The Application enables the use of third-party and open-source AI models. These models may generate content that is inaccurate, misleading, offensive, or otherwise harmful.

  • All AI-generated content is produced automatically by models selected and executed by you
  • The Developer does not review, approve, or endorse any generated content
  • The Developer has no ability to prevent or alter specific outputs generated by local models

You are solely responsible for how you interpret, use, share, or rely on any AI-generated content.

3. No Warranties

THE APPLICATION AND ALL AI-GENERATED CONTENT ARE PROVIDED "AS IS" AND "AS AVAILABLE", WITHOUT WARRANTIES OF ANY KIND. TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THE DEVELOPER DISCLAIMS ALL WARRANTIES, INCLUDING WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, ACCURACY, RELIABILITY, AND SAFETY OF CONTENT.

4. Limitation of Liability

To the maximum extent permitted by law, the Developer shall not be liable for any direct, indirect, incidental, consequential, special, or punitive damages arising from AI-generated content, user prompts, model behavior, or third-party models. You assume all risks associated with use of the Application.

5. User Responsibility

You agree that you are solely responsible for selecting and configuring AI models, ensuring compliance with applicable laws, evaluating the accuracy and legality of AI-generated content, and any actions taken based on AI outputs. The Application is intended for informational and experimental purposes only and must not be relied upon as professional, legal, medical, or financial advice.

6. Third-Party Software & Open Source

The Application incorporates third-party and open-source components governed by their own licenses. The Application itself is licensed under the Apache License, Version 2.0. In the event of a conflict between these Terms and an open-source license, the open-source license shall govern for covered components.

8. Reporting Inappropriate Content

If you encounter AI-generated content that is inappropriate or harmful, email [email protected] with subject line "InferencePort AI Inappropriate Content Disclosure". Reports without this subject line may not be reviewed.

Reports are reviewed within 1–2 weeks. Individual responses are not guaranteed. We reserve the right to ignore communications submitted in bad faith.

By using InferencePort AI, you acknowledge that you have read, understood, and agreed to these Terms. We reserve the right to change these terms at any time without further notice.


Contact

🔒
Security Disclosures
🚩
Content Reports
💬
General Questions
🗑️