AgentOne

Terms of Service

Effective date: November 3, 2026

These Terms of Service ("Terms") govern your access to and use of the AgentOne desktop application, the website located at www.agent-one.dev, and any related services (collectively, the "Service"), operated by CodeWorks Labs LLC d/b/a AgentOne ("we," "us," or "our"). By accessing or using the Service, you agree to be bound by these Terms. If you do not agree, do not use the Service.

1. Eligibility

You must be at least 16 years of age to use the Service. By using the Service, you represent and warrant that you meet this age requirement. If you are under 16, you may not create an account or use any part of the Service.

2. Accounts

To access certain features of the Service (such as chat sync, settings sync, and device authorization), you must create an account. You may upload a profile image to your account. When you create an account, you agree to:

  • Provide accurate, current, and complete information during registration.
  • Maintain the security of your account credentials and not share them with others.
  • Notify us promptly of any unauthorized use of your account.
  • Accept responsibility for all activity that occurs under your account.

We reserve the right to suspend or terminate accounts that violate these Terms or that we reasonably believe are being used fraudulently.

3. Description of the Service

AgentOne is a desktop application that provides an AI agent and deep research interface. Key aspects of the Service include:

  • AgentOne-provided models. AgentOne provides a hosted default AI model as the default experience. When you use AgentOne-provided models, your requests are processed through our infrastructure and routed to underlying AI providers. You do not need to supply your own API keys to use AgentOne-provided models.
  • Bring Your Own Keys. You may also connect to third-party AI providers (such as OpenRouter, Groq, Google Generative AI, and Cerebras) using API keys that you supply, or use local models through tools such as Ollama or LM Studio. These connections are made directly from your device.
  • Chat sync. Your chat history and messages are synced to our servers when you are signed in, enabling you to access your conversations across devices. A local copy is also maintained on your device.
  • Optional settings sync. If you create an account and enable settings sync, your non-sensitive application preferences will be stored on our servers to enable cross-device synchronization.
  • Optional API key sync. You may separately opt in to sync your third-party API keys across devices. If enabled, your API keys are encrypted before transmission and stored on our servers in encrypted form. This is a separate opt-in from settings sync and can be disabled at any time.
  • Built-in tools. The application includes built-in tools such as web search and URL content fetching, which execute locally on your device. You can turn individual built-in tools on or off in the application's settings.
  • Extensions. You can install extensions based on the Model Context Protocol (MCP), including extensions listed in the public MCP Registry. Some extensions run as programs on your device with your user permissions; others connect to remote servers operated by third parties. Installed extensions and their configurations are stored on your device and are not synced between devices.
  • Scheduled Agents. You can create scheduled agents that run a prompt automatically on a schedule you choose. Scheduled agents are stored on your device and registered with your operating system's built-in scheduler, which opens the application to start each run in a new chat. See section 7.

4. Free and Paid Tiers

The Service operates on a freemium model. Certain features may be available for free, while others may require a paid subscription or one-time payment. We reserve the right to change our pricing, add or remove features from free or paid tiers, or introduce new tiers at any time. If you are on a paid plan, we will provide reasonable notice before changes that materially affect your subscription. Fees, once paid, are non-refundable except where required by applicable law.

Use of AgentOne-provided models is measured in credits. Credits are consumed based on your usage (such as the number of tokens processed), and the application may display your credit balance and usage for each chat. Payments and subscriptions are processed by our payment provider, Polar, and are also subject to its terms.

5. Your Responsibilities

You agree that you will:

  • Comply with all applicable laws and regulations when using the Service.
  • Use your own valid API keys obtained in accordance with the terms of the respective third-party AI providers.
  • Be solely responsible for the content of your prompts, conversations, and any outputs generated through the Service.
  • Not use the Service to generate content that is illegal, harmful, threatening, abusive, defamatory, or otherwise objectionable.
  • Not attempt to reverse engineer, decompile, disassemble, or otherwise derive the source code of our proprietary hosted services (described in section 8) except where expressly permitted by applicable law. This restriction does not apply to the open-source desktop application.
  • Review the extensions you install and the tool requests you approve. Extensions that run on your device can access your files and system with your user permissions.
  • Not interfere with or disrupt the integrity or performance of the Service or its related systems.
  • Not use automated systems, bots, or scripts to access the Service in a manner that exceeds reasonable use.

6. Third-Party Services and API Keys

The Service provides AgentOne-hosted models by default and also enables you to connect to third-party AI providers and MCP servers using your own credentials and configurations. You acknowledge and agree that:

  • When using AgentOne-provided models, your requests are processed through our infrastructure. We route these requests to underlying AI providers and are not responsible for the accuracy, quality, or content of their responses.
  • Your use of third-party AI providers with your own API keys is governed by their respective terms of service and privacy policies, not ours.
  • We are not responsible for the availability, accuracy, quality, or content of responses from third-party AI providers.
  • You are responsible for any costs, fees, or charges incurred through your use of third-party API keys.
  • You are responsible for the security of your API keys. By default, we store them only in your device's secure credential store. If you opt in to API key sync, your keys are encrypted and stored on our servers to enable cross-device access.
  • We are not responsible for any data processing performed by MCP servers you configure, including self-hosted or third-party MCP servers.

7. Scheduled Agents and Automated Actions

Scheduled agents run your prompts automatically, without you actively starting each run. You acknowledge and agree that:

  • You are responsible for the scheduled agents you create or approve, including scheduled agents that AgentOne creates or changes at your request, and for any actions, outputs, and charges (including credit usage and third-party API costs) that result from their runs.
  • Scheduled runs use your application settings, default model, tools, and extensions at the time of the run, and follow your tool approval settings. Tools you have allowed to run without approval may run without you present.
  • Scheduled runs depend on your device and operating system. Runs may be delayed, combined, or skipped if your device is off, asleep, or offline, or if your operating system's scheduler does not launch the application. We do not guarantee that any scheduled run will occur at a particular time or at all.

9. Your Content

You retain ownership of any content you create, input, or generate using the Service, including your prompts, chat messages, uploaded profile images, and other data. We do not claim any ownership rights over your content. Your chat history is synced to our servers to enable cross-device access. When using your own API keys, conversations are processed directly by third-party AI providers. When using AgentOne-provided models, your requests are routed through our infrastructure to underlying AI providers, and we retain records of those requests for a limited period as described in our Privacy Policy.

We access the content of your conversations only as reasonably necessary to provide and maintain the Service, to investigate suspected violations of these Terms, to address security or abuse concerns, and to comply with applicable law. Access is limited to authorized personnel. We do not use your content to train AI models.

10. Disclaimer of Warranties

THE SERVICE IS PROVIDED "AS IS" AND "AS AVAILABLE" WITHOUT WARRANTIES OF ANY KIND, WHETHER EXPRESS, IMPLIED, OR STATUTORY, INCLUDING BUT NOT LIMITED TO IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. WE DO NOT WARRANT THAT THE SERVICE WILL BE UNINTERRUPTED, ERROR-FREE, OR SECURE, OR THAT ANY DEFECTS WILL BE CORRECTED.

AI-generated content may be inaccurate, incomplete, or misleading. You are solely responsible for evaluating and verifying any output produced through the Service. We make no representations or warranties regarding the accuracy or reliability of AI-generated content.

11. Limitation of Liability

TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL CODEWORKS LABS LLC D/B/A AGENTONE, ITS AFFILIATES, OR ITS CONTRIBUTORS BE LIABLE FOR ANY INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL, OR PUNITIVE DAMAGES, OR ANY LOSS OF PROFITS, DATA, USE, OR GOODWILL, ARISING OUT OF OR IN CONNECTION WITH YOUR USE OF OR INABILITY TO USE THE SERVICE, REGARDLESS OF THE THEORY OF LIABILITY.

OUR TOTAL AGGREGATE LIABILITY FOR ALL CLAIMS RELATED TO THE SERVICE SHALL NOT EXCEED THE AMOUNT YOU PAID US, IF ANY, IN THE TWELVE (12) MONTHS PRECEDING THE CLAIM, OR FIFTY US DOLLARS ($50.00), WHICHEVER IS GREATER.

12. Indemnification

You agree to indemnify, defend, and hold harmless CodeWorks Labs LLC d/b/a AgentOne and its contributors from and against any claims, liabilities, damages, losses, and expenses (including reasonable legal fees) arising out of or related to: (a) your use of the Service; (b) your violation of these Terms; (c) your violation of any applicable law or third-party rights; or (d) content you generate or transmit through the Service.

13. Termination

You may stop using the Service and delete your account at any time. We may suspend or terminate your access to the Service at our discretion, with or without notice, for any reason, including but not limited to a violation of these Terms.

Upon termination, your right to use the Service ceases immediately. Server-side data associated with your account (including account information, synced chat history, synced settings, synced API keys, uploaded profile images, and request records) will be deleted, except for information we are required to retain by law or reasonably need to retain to enforce these Terms or resolve disputes, as described in our Privacy Policy. Locally stored data on your device remains under your control.

14. Updates and Changes to the Service

We may update, modify, or discontinue features of the Service at any time without prior notice. The desktop application includes an automatic update mechanism; by using the application, you consent to receiving updates. The application also periodically downloads updated lists of available AI models and extensions. We are not liable for any modification, suspension, or discontinuation of any part of the Service.

15. Changes to These Terms

We may update these Terms from time to time. When we do, we will revise the effective date at the top of this page. We encourage you to review these Terms periodically. Your continued use of the Service after any changes constitutes acceptance of the updated Terms. If you do not agree to the revised Terms, you must stop using the Service.

16. Governing Law

These Terms shall be governed by and construed in accordance with the laws of the United States and the State of Oklahoma, without regard to conflict of law principles. Any disputes arising from or relating to these Terms or the Service shall be resolved in the state or federal courts located in Oklahoma, and you consent to the personal jurisdiction of such courts.

17. Severability

If any provision of these Terms is found to be unenforceable or invalid, that provision shall be limited or eliminated to the minimum extent necessary, and the remaining provisions shall remain in full force and effect.

18. Entire Agreement

These Terms, together with our Privacy Policy, constitute the entire agreement between you and CodeWorks Labs LLC d/b/a AgentOne regarding your use of the Service and supersede any prior agreements or understandings.

19. Contact Us

If you have any questions about these Terms, contact us at [email protected].