# AutoGPT Platform for AI agents with a visual builder, marketplace, schedules and triggers; as a paid cloud service or to self-host. Canonical profile: https://ki-agentenkompass.de/en/agents/autogpt/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview AutoGPT consists of the platform (Polyform Shield) and the older AutoGPT Classic (MIT), which the documentation says is no longer supported. Determinist Ltd, trading as AutoGPT, is responsible for the hosted platform. - Provider: Significant Gravitas / Determinist Ltd - Product family: AutoGPT - Profile type: Platform for AI agents and workflows - Environment: Browser (cloud platform) or Docker on Linux, macOS and Windows (WSL 2) - Connections: Blocks and integrations, webhook triggers, marketplace, API and MCP server - Setup: Create an account on the platform or run the Docker container yourself and add your own model keys. - Pricing model: Cloud: Pro $50 per month, with a 7-day trial for eligible new accounts; Max $320. Workflow runs draw on credits. Self-hosting is free; you provide infrastructure and model access. ## Key features ### Visual workflow builder You connect blocks, branch logic and control the individual steps. Source: https://agpt.co ### AutoPilot and Otto AutoPilot carries out supported actions in conversation: running agents, building from a description, searching the marketplace and setting up schedules. According to the website, Otto coordinates specialist Experts. Source: https://agpt.co/docs/platform/using-the-platform/autopilot.md ### Schedules and webhook triggers Agents run at set times or start when an external service sends data to a webhook URL. Source: https://agpt.co/docs/platform/using-the-platform/scheduling-and-triggers.md ### Marketplace and library Ready-made agents can be added from the marketplace to your own library and run from there. Source: https://agpt.co/docs/platform/using-the-platform/getting-started-cloud.md ### API and MCP server Through an API and an MCP server, AI tools can search, build and run agents and read results. Access uses an API key with permissions. Source: https://agpt.co/docs/platform/api-and-integrations/api-guide/mcp-server.md ### Human review within a run A block can pause a run until a person approves or rejects data. According to the documentation, the run waits indefinitely. Source: https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md ### Self-hosting with Docker A single container holds the interface, backend and databases; state is kept in a Docker volume. Source: https://agpt.co/docs/platform/self-hosting/single-container ## Example workflows ### Recurring research on a schedule - Your input: An agent with input and output blocks and fixed inputs for the schedule. - Possible result: The agent runs at the set times in your timezone. - What to check: Read the run results and check that all required outputs are present. ### Webhook starts agent with approval - Your input: An agent with a trigger block and a block for human approval. - Possible result: The run starts on incoming data and pauses before the approval. - What to check: Answer waiting reviews; without an answer the run waits indefinitely. ## Requirements and limits ### Paid cloud service Requirement: The hosted platform is a paid service. Eligible new accounts can start Pro with a 7-day trial that requires a card; workflow runs draw on credits. Source: https://agpt.co/pricing/ ### Self-hosting: Docker and model keys Requirement: You need Docker, according to the guide more than 5 to 6 GiB of RAM, and model access of your own for AutoPilot and memory: OpenRouter plus OpenAI, an Anthropic key in addition to both, or a local OpenAI-compatible server. Source: https://agpt.co/docs/platform/self-hosting/single-container ### Single container is not multi-tenant Limitation: The guide says explicitly that the container is not a turnkey multi-tenant distribution. Uploaded files are not scanned for malware, and you set up TLS for remote access yourself. Source: https://agpt.co/docs/platform/self-hosting/single-container ### Managed services missing when self-hosting Limitation: According to the pricing page, hosted billing, managed credentials and marketplace publishing are not part of self-hosting. Source: https://agpt.co/pricing/ ### AutoGPT Classic no longer supported Limitation: According to the documentation, Classic is not supported from a security perspective; dependencies are not updated and issues are not fixed. Source: https://agpt.co/docs/classic/autogpt-classic/introduction.md ### Completed run does not mean error-free Limitation: A run can count as completed even though a block failed. You check that the outputs you need are present. Source: https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md ### Team features Not yet confirmed: The pricing page lists Team as coming soon, with multi-user workspaces and admin roles; contact is through sales. Source: https://agpt.co/pricing/ ## A good fit if … - you want to build recurring processes as visual workflows with a schedule or webhook trigger - you want to run the platform on your own infrastructure with your own model keys - you want to control agents from an AI tool through the MCP server ## Less suitable if … - you expect free cloud use without a card on file - you must process customer data in a documented EU hosting region - you need ready multi-user and admin management today Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice In the cloud, models are built in, the Pro plan promises access to virtually any leading model according to the provider, and you pick them in the AI blocks. Custom endpoints and local models work only when self-hosting: there you use your own keys, Ollama for blocks and any OpenAI-compatible endpoint for chat. Ollama models outside the default list need their own catalog entry. - Model families named: Anthropic (Claude), OpenAI (GPT), Google (Gemini), xAI (Grok), Meta (Llama, Muse), Mistral, Cohere, Microsoft (MAI), Z.ai (GLM), DeepSeek, Alibaba (Qwen), Moonshot (Kimi) · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes - Depends on: Plan Documented · Sources accessed on: 2026-11-05 - [AutoGPT: Pricing](https://agpt.co/pricing/) - [AutoGPT: AutoPilot with a local LLM](https://agpt.co/docs/platform/using-ai-services/copilot-local-llm.md) - [AutoGPT: Using Ollama](https://agpt.co/docs/platform/ollama) - [AutoGPT: Built-in blocks](https://agpt.co/integrations/built-in/) - [AutoGPT: README](https://raw.githubusercontent.com/Significant-Gravitas/AutoGPT/master/README.md) ## Europe & regional availability Privacy policy, subprocessor list, terms of use and pricing page reviewed. No statement on availability in Europe was found. Reviewed scope: Hosted platform and self-hosted installation Reviewed on: 2026-11-05 ### Availability in Europe: no statement Availability still unclear The reviewed pages name no country or region release for sign-up and payment. The terms are governed by the law of England and Wales; mandatory consumer protections of your country of residence are preserved according to the terms. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: The reviewed sources name no country release for this. Official source: https://agpt.co/pricing/ Official source: https://agpt.co/legal/platform-terms-of-use/ ### Data processing mainly in the US Availability still unclear According to the list, Google Cloud, Supabase and the model providers OpenAI and Anthropic are in the US. The list names no EU hosting option for the platform. Langfuse (AutoPilot traces) and a PostHog instance are among those located in the EU. For transfers the page cites standard contractual clauses or the EU-US Data Privacy Framework; the privacy policy refers to the UK GDPR. Region covered: EU/EEA Documented reason: The sources make no statement on a hosting region in Europe for customer data. Official source: https://agpt.co/legal/subprocessors/ Official source: https://agpt.co/legal/platform-privacy-policy/ ### Self-hosting: data stays with you Availability still unclear When self-hosting, all durable state lives in your own Docker volume. The reviewed pages say nothing about Europe; you choose model providers and their region yourself. Region covered: EU/EEA Documented reason: The reviewed sources name no country release for this. Official source: https://agpt.co/docs/platform/self-hosting/single-container Official source: https://agpt.co/docs/platform/using-ai-services/copilot-local-llm.md ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Cloud account on the platform or your own installation Sources reviewed: 2026-11-05 ### Account used Documented: You create an account on platform.agpt.co. You connect services by OAuth, API key or username and password; credentials are reusable and each block or task keeps its selected reference. The page does not say how they are stored. Evidence: https://agpt.co/docs/platform/using-the-platform/getting-started-cloud.md Evidence: https://agpt.co/docs/platform/using-the-platform/integrations-and-credentials.md ### Admin approval Documented with conditions: Team with admin roles and approvals is listed on the pricing page as coming soon. On the website you can set spending thresholds per Expert. No admin approval process for organisations is described. Evidence: https://agpt.co/pricing/ Evidence: https://agpt.co ### Data access & team sharing Documented: Agents use the connections you give them. The MCP server acts on your AutoGPT account and lists only the tools the API key’s permissions allow; some tools need no permission. The key reaches only its own organisation’s resources. When connecting MCP services, the page advises checking the requested permissions. Evidence: https://agpt.co/docs/platform/api-and-integrations/api-guide/mcp-server.md Evidence: https://agpt.co/docs/platform/using-the-platform/integrations-and-credentials.md ## Prices and included usage Pricing checked: 2026-11-05 Cloud: Pro $50 per month after a 7-day trial, Max $320 per month, Team announced. Workflow runs are paid from a credit wallet on every plan. Self-hosting is free. ### Pro $50 per month, after a 7-day trial for eligible new accounts Access to models, Experts, Otto chat, visual builder, connections and scheduled workflows; chat usage is covered by the subscription. Price source: https://agpt.co/pricing/ ### Pro (annual) $510 per year, equal to $42.50 per month As Pro, billed annually. Price source: https://agpt.co ### Max $320 per month Everything in Pro, plus 8.5x Pro usage, 5x file storage, early feature access and priority support. Price source: https://agpt.co/pricing/ ### Team Coming soon, contact sales Multi-user workspaces, admin roles, centralised billing and approvals are listed. Price source: https://agpt.co/pricing/ ### Self-hosted No software fee stated Platform via Docker with your own infrastructure and model keys. Price source: https://agpt.co The pricing page does not clearly show which plans can top up credits. Pricing details: https://agpt.co/pricing/ ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Cloud operation and self-hosting Sources reviewed: 2026-11-05 ### Files and working state Documented: When self-hosting with the single-container image, all durable state lives in the Docker volume under /data: configuration, databases, memory and workspaces. You keep the volume when replacing the container. Evidence: https://agpt.co/docs/platform/self-hosting/single-container Evidence: https://agpt.co/docs/platform/self-hosting/getting-started ### Sign-ins Documented with conditions: You connect services by OAuth, API key or password. The reviewed pages do not say how long access lasts or how it is renewed. Evidence: https://agpt.co/docs/platform/using-the-platform/integrations-and-credentials.md ### Starting further runs Documented: Schedules start agents at fixed times in your timezone; the API uses cron expressions. Triggers start an agent when an external service sends to a webhook URL, and such agents cannot be started manually. Runs can be stopped through the API. Evidence: https://agpt.co/docs/platform/using-the-platform/scheduling-and-triggers.md Evidence: https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md ### Human intervention Documented: A block can put a run into REVIEW until a person approves or rejects; the run waits indefinitely. If your integration cannot answer, the documentation names handing over to a person, answering yourself or stopping the run. For unattended agents, reviews can be turned off, and then every review counts as approved. Evidence: https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md ### Detecting errors Documented: A run is FAILED when it could not continue; errors are in node_executions. A run can be COMPLETED even though a block failed, so you check the outputs you need. The scheduling page names no failure notifications. Evidence: https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md Evidence: https://agpt.co/docs/platform/using-the-platform/scheduling-and-triggers.md ### Resuming after failures Documented with conditions: When self-hosting, you take a cold backup before an upgrade, replace the container with the same volume and, if needed, restore the matching archive into a new volume. You must not run an older image against an already migrated volume. Runs still executing when the container stops are abandoned and do not resume; you start a new run. Evidence: https://agpt.co/docs/platform/self-hosting/single-container ### Editorial assessment Schedules, triggers and reviews are documented. When self-hosting you are responsible for backups, TLS and updates, and failure notifications are not described. ## Memory and conversation continuity Scope: AutoPilot memory and learned skills of the platform Sources accessed: 2026-11-05 When self-hosted, AutoPilot memory sits in a graph database in the Docker volume; inspection and deletion are documented only for learned skills. ### Storage and scope Partly documented: When self-hosted, FalkorDB stores memory under /data/falkordb in the Docker volume. Learned skills are saved as immutable versions, at most 150 per account or Expert. The reviewed pages do not say where the cloud platform stores memory. - [AutoGPT: single container](https://agpt.co/docs/platform/self-hosting/single-container) - [AutoGPT: nightly skill learning](https://agpt.co/docs/platform/using-ai-services/skill-learning.md) ### Selection and timing Partly documented: Nightly skill learning is off by default and enabled per cohort through a feature flag. It runs at 03:00 in the person’s timezone and proposes skills from verified work. The pages do not describe how AutoPilot memory selects what to keep. - [AutoGPT: nightly skill learning](https://agpt.co/docs/platform/using-ai-services/skill-learning.md) ### Inspect, edit and delete Partly documented: For skills you can view history and sources, pause learning, edit, restore a version and delete; individual conversations can be excluded from learning. The pages describe no controls for individual memory entries. - [AutoGPT: nightly skill learning](https://agpt.co/docs/platform/using-ai-services/skill-learning.md) ### Agent and channel boundaries Partly documented: Skills are private to the account and the Expert that produced them; Experts keep separate conversations. Personal chats teach the personal assistant, Expert chats only that Expert. Separation of graph memory per person is not described. - [AutoGPT: nightly skill learning](https://agpt.co/docs/platform/using-ai-services/skill-learning.md) - [AutoGPT: Experts](https://agpt.co/experts/) - [AutoGPT: single container](https://agpt.co/docs/platform/self-hosting/single-container) ### Retrieval Not publicly established: The reviewed pages do not describe how memory is retrieved when answering. Extracting memory needs a model and an embedding model, for example a local one such as nomic-embed-text. - [AutoGPT: AutoPilot with a local model](https://agpt.co/docs/platform/using-ai-services/copilot-local-llm.md) ### Session reset and compaction Partly documented: Resetting memory per person is not documented. When self-hosted, all durable state lives in the volume under /data, and each installation should use its own volume. The pages say nothing about compaction of long chats. - [AutoGPT: single container](https://agpt.co/docs/platform/self-hosting/single-container) ## Context The cloud platform is paid and workflow runs draw on credits. Self-hosting needs your own infrastructure and model keys, and managed services such as billing or marketplace publishing are not part of it. According to the subprocessor list, the hosted platform processes data mainly in the US. Official website, pricing page, documentation, legal pages and repository reviewed. Feature descriptions come from the provider; example tasks are editorial. Hands-on tests are still pending. ## Open points Europe, availability still unclear: - Availability in Europe: no statement - Data processing mainly in the US - Self-hosting: data stays with you Requirements and limits, not yet confirmed: - Team features ## Sources - https://agpt.co - https://agpt.co/pricing/ - https://github.com/Significant-Gravitas/AutoGPT - https://agpt.co/docs/platform/self-hosting/single-container - https://agpt.co/docs/platform/self-hosting/getting-started - https://agpt.co/docs/platform/using-the-platform/autopilot.md - https://agpt.co/docs/platform/using-the-platform/scheduling-and-triggers.md - https://agpt.co/docs/platform/using-ai-services/skill-learning.md - https://agpt.co/docs/platform/using-the-platform/integrations-and-credentials.md - https://agpt.co/docs/platform/using-the-platform/getting-started-cloud.md - https://agpt.co/docs/platform/api-and-integrations/api-guide/running-agents.md - https://agpt.co/docs/platform/api-and-integrations/api-guide/mcp-server.md - https://agpt.co/docs/platform/using-ai-services/copilot-local-llm.md - https://agpt.co/docs/classic/autogpt-classic/introduction.md - https://agpt.co/legal/platform-privacy-policy/ - https://agpt.co/legal/subprocessors/ - https://agpt.co/legal/platform-terms-of-use/ - https://agpt.co/experts/ ## Provider Determinist Ltd offers the platform under the name AutoGPT; the source code is in the Significant-Gravitas/AutoGPT repository. - Operator: Determinist Ltd (AutoGPT) - Organization: Provider - Website: https://agpt.co - Reviewed: 2026-11-05 - Repository: https://github.com/Significant-Gravitas/AutoGPT - GitHub-Stars: 187909 (2026-11-05) - License: Polyform Shield (autogpt_platform), MIT (classic and rest) - Provider source: https://agpt.co - Provider source: https://agpt.co/legal/platform-privacy-policy/ - Provider source: https://github.com/Significant-Gravitas/AutoGPT [Sources and method](https://ki-agentenkompass.de/en/sources/)