Automation workspace with AI chat, agents, flows, tables, app connections, and self-hosting options.
Best for: Visual flows and AI agents
AI agent platform for coordinating experts and recurring work, with a self-hosted path and managed service.
Best suited to
Agent coordination and Recurring tasks
AI agent platform for coordinating experts and recurring work, with a self-hosted path and managed service.
Define a bounded task, supply the necessary context and tools, and test the agent's actions before recurring use.
Access and pricing: Self-hosting requires your own infrastructure and model keys. Platform code uses Polyform Shield; classic components use MIT. Managed service access and model costs are separate.
According to the official site, AutoGPT's hosted platform lets you brief a team of AI "Experts" in plain language, with an assistant called Otto coordinating them. The site lists Experts for jobs such as SEO content, sales prospecting, LinkedIn posts and executive assistance, and mentions connecting apps like Google Drive and WordPress. You can set spending limits per Expert, which helps keep recurring work predictable.
Based on documentation, there are two routes. For the managed service, start the 7-day Pro trial (a card is required, with no subscription charge at signup), brief one Expert on a single narrow task and read its output closely. For the self-hosted route, the site says a single Docker command is enough to run it for free, though you provide the infrastructure and model access yourself.
There is no permanent free hosted plan listed. After the trial, Pro is $50/month ($510/year) and Max is $320/month. Workflow runs also draw on a credit wallet, so cost depends on how much you run. Review what each Expert is allowed to do before scheduling anything recurring.
Agent coordination
Recurring tasks
Connected tools
Self-hosted deployment
No permanent free hosted plan: eligible new accounts get a 7-day Pro trial (card required, no charge at signup). Pro is $50/month ($510/year) after the trial; Max is $320/month. Workflow runs use a credit wallet. Self-hosting is free via Docker but you supply infrastructure and model access.
Plan information can change. Prices and conditions are set by the provider. Information checked 2026-10-06.
Source for access detailsOne email a week: new free AI tools, prompts and free-plan changes. No spam, unsubscribe any time.
By subscribing you agree to receive this email from Genius Forges and to us storing your address to send it. We may ask you to confirm by email. Every email has an unsubscribe link. See our privacy policy.
Define a bounded task, supply the necessary context and tools, and test the agent's actions before recurring use.
Self-hosting requires your own infrastructure and model keys. Platform code uses Polyform Shield; classic components use MIT. Managed service access and model costs are separate.
Official-source information was reviewed on 2026-10-06. Plans and limits can change; check the linked provider source before subscribing.
The self-hosted route is free to run with a single Docker command, but you pay for your own infrastructure and model access. The hosted platform has no permanent free plan; new eligible accounts get a 7-day Pro trial that requires a card. Check agpt.co for current terms.
Per the official site, Pro is $50/month or $510/year, and Max is $320/month with 8.5 times the Pro usage. Workflow runs draw on a credit wallet on every plan, and hiring an Expert has no separate fee. Prices can change, so confirm before subscribing.
Yes. The official site says you can self-host AutoGPT for free using a single Docker command. You are responsible for the infrastructure and for supplying model access, so model usage costs still apply. Review the licence terms in the GitHub repository before commercial use.
Tell us what needs improving. No account or private output required.
Report incorrect information or a broken linkPrompt
Prompt
Prompt
Learn AI
Learn AI
Automation workspace with AI chat, agents, flows, tables, app connections, and self-hosting options.
Best for: Visual flows and AI agents
Terminal-based AI coding tool that edits an existing codebase and works with Git and chosen model providers.
Best for: Developers making reviewable code changes from the terminal
Experimental Python framework for registering functions and exploring self-building AI workflows.
Best for: Function registration and Function dependencies