Spaces:
Runtime error
Runtime error
| --- | |
| title: FAQ | |
| description: Get answers to the most frequently asked questions about AgentGPT | |
| icon: "question" | |
| --- | |
| Discover answers to the most frequently asked questions about AgentGPT. If your question isn't covered here, feel free to connect with our team on [Discord](https://discord.gg/jdSBAnmdnY) or [GitHub](https://github.com/reworkd/AgentGPT). | |
| ## Agent issues | |
| <AccordionGroup> | |
| <Accordion title="AgentGPT said it made a file / database / script, where can I find it?"> | |
| At present, AgentGPT does not have the capability to generate outputs in this | |
| way. However, this is a feature we're actively developing. To keep updated on | |
| this, check out our [roadmap](/essentials/roadmap). | |
| </Accordion> | |
| <Accordion title="Did AgentGPT really email 100 people?"> | |
| Not yet! We're looking into implementing this functionality. To see when this | |
| might be available, take a look at our [roadmap](/essentials/roadmap). We guarantee that | |
| actions such as "sending an email" will only occur with your explicit | |
| permission. | |
| </Accordion> | |
| <Accordion title="My agent keeps running out of loops!"> | |
| Due to limitations on API usage and infrastructure costs, there's a cap on how | |
| much the Agent can run. To circumvent this, consider hosting AgentGPT locally | |
| using your own API key. Alternatively, subscribing to our pro plan will allow | |
| for increased limits. More details can be found in our [setup | |
| documentation](/essentials/roadmap). | |
| </Accordion> | |
| <Accordion title="My Agent was running smoothly, but then it stopped! Can I resume from where it left off?"> | |
| Currently, each Agent run is independent, so resuming isn't possible. However, | |
| you can initiate another AgentGPT run using information from the previous run. | |
| We plan on adding this feature in the future. Stay updated via our | |
| [roadmap](/essentials/roadmap). | |
| </Accordion> | |
| <Accordion title="Can AgentGPT use GPT-4?"> | |
| Currently, free-tier users of AgentGPT utilize GPT-3.5, while PRO users have | |
| access to GPT-4. If you have API access to GPT-4, you can run AgentGPT locally | |
| using your API key. | |
| </Accordion> | |
| <Accordion title="Why does the output keep getting cut off?"> | |
| The output length is limited to manage generation costs on our end. If you're | |
| using your own API key, you can adjust the output length within the advanced | |
| settings by increasing the token count. If you're a Pro user or are a running | |
| AgentGPT locally, you can adjust the output length winthin the advanced | |
| settings | |
| </Accordion> | |
| </AccordionGroup> | |
| ## Misc | |
| <AccordionGroup> | |
| <Accordion title="How is AgentGPT different from ChatGPT?"> | |
| While ChatGPT is designed to answer specific questions and maintain a | |
| conversation, AgentGPT is a platform where you can configure an AI agent to | |
| achieve a broad goal. | |
| </Accordion> | |
| <Accordion title="How is AgentGPT different from AutoGPT?"> | |
| Both AgentGPT and AutoGPT are autonomous AI agent projects. However, while | |
| AutoGPT runs locally, AgentGPT is a web-based platform. | |
| </Accordion> | |
| <Accordion title="What can AgentGPT do?"> | |
| AgentGPT boasts a wide array of capabilities and we're always working to | |
| expand them. To see some of its applications, visit our [usecases](/essentials/usecases) | |
| page. | |
| </Accordion> | |
| <Accordion title="Can AgentGPT access the internet?"> | |
| Yes, AgentGPT does have internet access. | |
| </Accordion> | |
| </AccordionGroup> | |
| ## Local contribution issues | |
| <AccordionGroup> | |
| <Accordion title="I'm experiencing issues setting up AgentGPT locally!"> | |
| For troubleshooting, refer to our [setup guide](/development/setup). If your | |
| issue persists, you're welcome to submit an [issue on | |
| GitHub](https://github.com/reworkd/AgentGPT/issues). | |
| </Accordion> | |
| </AccordionGroup> | |