AutoGPT Platform
Visual builder for long-running AI agents and workflows, self-hostable as a single container.
Quick answer
AutoGPT Platform is a visual builder for long-running AI agents and workflows, self-hostable as a single container, listed under AI app & agent builders. A typical small-business use: recurring content, research or lead-qualification agents that run on a schedule. Official hardware: minimum 6 GB RAM. That fits a Hetzner Cloud CPX32 server at about €35.99/month (server only, excl. VAT). License: Polyform Shield 1.0.0 (autogpt_platform/); MIT for the rest, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 28, 2026.
What is AutoGPT Platform?
The AutoGPT Platform is the current product from the team behind the original AutoGPT agent. It offers a visual block-based builder for agents and workflows, a marketplace of ready-made agents, scheduling and integrations, and runs with your own model credentials or a local model such as Ollama. Self-hosting is easiest with the official single-container image; a Docker Compose setup with one service per container is also documented. A paid hosted version exists.
Where it fits in a 10–200 person business
- Recurring content, research or lead-qualification agents that run on a schedule
- Prototype multi-step agent workflows visually before wiring them into business systems
- Run marketplace agents on your own server with your own model keys
These use cases are our editorial suggestions, not claims made by the project.
Can a business use AutoGPT Platform? (license)
| License | Polyform Shield 1.0.0 (autogpt_platform/); MIT for the rest |
|---|---|
| Type | Source-available: Code is public but commercial resale is restricted. |
| Internal business use | Allowed under the license text |
| What to watch | The platform code in autogpt_platform/ is under the Polyform Shield License: use and modification for your business are allowed, but you may not use it to offer a product or service that competes with AutoGPT. The classic agent, Forge and benchmark outside that folder are MIT. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does AutoGPT Platform phone home?
| Telemetry (usage data sent to the vendor) | Not documented |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Not documented |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does AutoGPT Platform need?
| Minimum | 6 GB RAM |
|---|---|
| Recommended | Not published |
The single-container guide asks for "more than the measured 5–6 GiB of appliance memory use, with additional headroom for agents, local models, and workload growth", says there is no measured minimum CPU count, and recommends SSD-class storage with room for the image, the /data volume and a full backup archive. Local models need extra memory.
How much does it cost to host AutoGPT Platform per month?
| Minimum spec | 6 GB RAM → CPX32 (4 vCPU, 8 GB, 160 GB disk) €35.99/mo |
|---|
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-25. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy AutoGPT Platform
Method: Docker (single container)
docker run -d \
--name autogpt \
--restart unless-stopped \
--shm-size 2g \
--ulimit nofile=65536:65536 \
--log-driver json-file \
--log-opt max-size=50m \
--log-opt max-file=5 \
-p 127.0.0.1:3000:3000 \
-e AUTOGPT_PUBLIC_URL=http://localhost:3000 \
-v autogpt-data:/data \
significantgravitas/autogpt:latest
# then create your account at http://localhost:3000 and promote it:
docker exec autogpt autogpt-admin promote [email protected] From the official instructions: github.com/Significant-Gravitas/AutoGPT#self-host-autogpt. Always check the source for the current version before you run it.
Known gotchas when self-hosting AutoGPT Platform
- New-account signup is open by default so the first admin can register; anyone who can reach the port can create an account until you set AUTH_SIGNUP_ALLOWLIST or AUTH_ALLOW_NEW_ACCOUNTS=false. Close signup while the app is still bound to localhost. source
- The image does not support required email verification, and without Postmark settings there is no password-reset email; store the admin password safely. source
- Polyform Shield forbids using the platform to offer a competing product or service, so it is not open source in the OSI sense; reselling it as a hosted agent platform is not allowed. source
- The default local profile is meant for single-tenant self-hosting; any multi-tenant deployment must set BEHAVE_AS=cloud, and the docs say that alone is not a complete hosted-mode switch. source
Alternatives in AI app & agent builders
- Dify Visual platform for building LLM apps, RAG chatbots, agents and workflows. Compare AutoGPT Platform vs Dify
- Langflow Visual builder for AI agents and RAG flows that you can deploy as APIs or MCP servers. Compare AutoGPT Platform vs Langflow
- Flowise Drag-and-drop builder for LLM agents and chatflows (archived August 2026).
- Sim Visual builder for AI agent workflows, with knowledge bases, integrations and an API. Compare AutoGPT Platform vs Sim
- Coze Studio Open-source edition of ByteDance's Coze agent-building platform. Compare AutoGPT Platform vs Coze Studio
AutoGPT Platform FAQ
How much RAM does AutoGPT Platform need?
The official minimum is 6 GB RAM. The single-container guide asks for "more than the measured 5–6 GiB of appliance memory use, with additional headroom for agents, local models, and workload growth", says there is no measured minimum CPU count, and recommends SSD-class storage with room for the image, the /data volume and a full backup archive. Local models need extra memory.
How much does it cost to self-host AutoGPT Platform?
The software is free to download. Based on the official minimum 6 GB RAM: That fits a Hetzner Cloud CPX32 server at about €35.99/month (server only, excl. VAT). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is AutoGPT Platform free for commercial use?
AutoGPT Platform is licensed under Polyform Shield 1.0.0 (autogpt_platform/); MIT for the rest (Source-available). Internal business use is allowed under the license text. The platform code in autogpt_platform/ is under the Polyform Shield License: use and modification for your business are allowed, but you may not use it to offer a product or service that competes with AutoGPT. The classic agent, Forge and benchmark outside that folder are MIT. This is a summary, not legal advice.
What are common problems when self-hosting AutoGPT Platform?
New-account signup is open by default so the first admin can register; anyone who can reach the port can create an account until you set AUTH_SIGNUP_ALLOWLIST or AUTH_ALLOW_NEW_ACCOUNTS=false. Close signup while the app is still bound to localhost. The image does not support required email verification, and without Postmark settings there is no password-reset email; store the admin password safely. Polyform Shield forbids using the platform to offer a competing product or service, so it is not open source in the OSI sense; reselling it as a hosted agent platform is not allowed. The default local profile is meant for single-tenant self-hosting; any multi-tenant deployment must set BEHAVE_AS=cloud, and the docs say that alone is not a complete hosted-mode switch.
Is AutoGPT Platform still maintained?
Yes, it is actively developed. Last commit: Oct 27, 2026. Latest release: autogpt-platform-beta-v0.10.0 (Oct 27, 2026). Checked Oct 28, 2026.
How do I install AutoGPT Platform?
The official method is Docker (single container). The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/Significant-Gravitas/AutoGPT#self-host-autogpt
What are self-hosted alternatives to AutoGPT Platform?
Other apps in AI app & agent builders: Dify, Langflow, Flowise, Sim, Coze Studio.
Sources
- GitHub repository: github.com/Significant-Gravitas/AutoGPT
- Official documentation, Hardware requirements, Gotcha 1, Gotcha 2, Gotcha 4: agpt.co/docs/platform/self-hosting/single-container
- License text, Gotcha 3: github.com/Significant-Gravitas/AutoGPT/blob/master/LICENSE
- Deploy instructions: github.com/Significant-Gravitas/AutoGPT#self-host-autogpt
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-28. Spotted something out of date? Tell us.