FastGPT
Knowledge-base Q&A and visual AI workflow platform.
Quick answer
FastGPT is a knowledge-base Q&A and visual AI workflow platform, listed under Knowledge base & RAG. A typical small-business use: customer-service assistant trained on product docs. Official hardware: minimum 2 vCPU · 4 GB RAM (recommended 2 vCPU · 8 GB RAM). That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT; €35.99/month for the recommended spec). License: FastGPT Open Source License (Apache-2.0 with conditions), which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is FastGPT?
FastGPT combines document import, vector search and a visual workflow editor for building question-answering and agent apps. It runs as a Docker Compose stack with MongoDB, a vector store (PgVector by default, or Milvus, OceanBase or SeekDB) and a model proxy.
Where it fits in a 10–200 person business
- Customer-service assistant trained on product docs
- Internal knowledge assistant for sales or operations teams
- Multi-step document review workflows
These use cases are our editorial suggestions, not claims made by the project.
Can a business use FastGPT? (license)
| License | FastGPT Open Source License (Apache-2.0 with conditions) |
|---|---|
| Type | Custom / conditional: Apache- or BSD-based with extra conditions (branding, multi-tenant SaaS, derivatives). |
| Internal business use | Allowed under the license text |
| What to watch | Commercial use is allowed. You need a commercial license to run a multi-tenant SaaS similar to FastGPT, or to remove or modify the logo or copyright in the console. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does FastGPT need?
| Minimum | 2 vCPU · 4 GB RAM |
|---|---|
| Recommended | 2 vCPU · 8 GB RAM |
Figures are for a test setup with PgVector. For about 1M vector groups the docs list a 4c8g minimum (4c16g recommended) with 50 GB disk.
How much does it cost to host FastGPT per month?
| Minimum spec | 2 vCPU · 4 GB RAM → CPX22 (2 vCPU, 4 GB, 80 GB disk) €19.99/mo |
|---|---|
| Recommended spec | 2 vCPU · 8 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 2026-10-22. "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 FastGPT
Method: Docker Compose (install script)
bash <(curl -fsSL https://doc.fastgpt.io/deploy/install.sh)
docker compose up -d
# http://localhost:3000, default user root / 1234From the official instructions: github.com/labring/FastGPT#readme. Always check the source for the current version before you run it.
Known gotchas when self-hosting FastGPT
Alternatives in Knowledge base & RAG
- RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare FastGPT vs RAGFlow
- AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs FastGPT
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare FastGPT vs PrivateGPT
- Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare FastGPT vs Onyx (formerly Danswer)
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare FastGPT vs MaxKB
FastGPT FAQ
How much RAM does FastGPT need?
The official minimum is 2 vCPU · 4 GB RAM. The recommended spec is 2 vCPU · 8 GB RAM. Figures are for a test setup with PgVector. For about 1M vector groups the docs list a 4c8g minimum (4c16g recommended) with 50 GB disk.
How much does it cost to self-host FastGPT?
The software is free to download. Based on the official minimum 2 vCPU · 4 GB RAM (recommended 2 vCPU · 8 GB RAM): That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT; €35.99/month for the recommended spec). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is FastGPT free for commercial use?
FastGPT is licensed under FastGPT Open Source License (Apache-2.0 with conditions) (Custom / conditional). Internal business use is allowed under the license text. Commercial use is allowed. You need a commercial license to run a multi-tenant SaaS similar to FastGPT, or to remove or modify the logo or copyright in the console. This is a summary, not legal advice.
What are common problems when self-hosting FastGPT?
If the CPU lacks AVX, MongoDB 5 will not start ("Illegal instruction"). Switch the image to mongo:4.4.29. Default credentials are root / 1234. Change them before exposing the instance.
Is FastGPT still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v4.17.2 (Oct 9, 2026). Checked Oct 22, 2026.
How do I install FastGPT?
The official method is Docker Compose (install script). The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/labring/FastGPT#readme
What are self-hosted alternatives to FastGPT?
Other apps in Knowledge base & RAG: RAGFlow, AnythingLLM, PrivateGPT, Onyx (formerly Danswer), MaxKB.
Sources
- GitHub repository: github.com/labring/FastGPT
- Official documentation, Hardware requirements, Gotcha 1: doc.fastgpt.io/self-host/deploy/docker
- License text: github.com/labring/FastGPT/blob/main/LICENSE
- Deploy instructions, Gotcha 2: github.com/labring/FastGPT#readme
- 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 2026-10-22. Spotted something out of date? Tell us.