DocsGPT

What is DocsGPT?

DocsGPT turns documents, websites and connected apps into AI agents that answer with citations. You can build agents and visual workflows, give them tools and MCP servers, and put them into a product through a chat widget, an OpenAI-compatible API or an MCP server, or into Slack, Discord and Telegram. It works with cloud models or local ones (Ollama, vLLM), including air-gapped installs. The whole project, including OIDC SSO, teams, roles, audit log and usage quotas, is MIT licensed.

Where it fits in a 10–200 person business

• Internal assistant over the company handbook, wiki and policies with cited answers
• Support chat widget on the website that answers from product documentation
• Agents that combine document search with API tools for routine questions

These use cases are our editorial suggestions, not claims made by the project.

Can a business use DocsGPT? (license)

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 DocsGPT phone home?

Checked against the project's own docs and repository on Oct 24, 2026. "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 DocsGPT need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

The deployment docs publish no CPU, RAM or disk requirements. They note that the optional decision model downloads about 0.5 GB and makes the backend hold up to 1 GB more memory. LLMs run through your configured provider or a local inference server.

Source: docs.docsgpt.cloud/Deploying/Docker-Deploying

How much does it cost to host DocsGPT per month?

How to deploy DocsGPT

Method: Docker Compose

mkdir docsgpt && cd docsgpt
curl -fsSLO https://raw.githubusercontent.com/arc53/DocsGPT/main/deployment/docker-compose-standalone.yaml
printf 'LLM_PROVIDER=docsgpt\nVITE_API_STREAMING=true\nINTERNAL_KEY=%s\nENCRYPTION_SECRET_KEY=%s\n' \
  "$(openssl rand -hex 16)" "$(openssl rand -hex 32)" > .env
docker compose -f docker-compose-standalone.yaml up -d
# open http://localhost:7091 (bound to 127.0.0.1 until you change DOCSGPT_BIND)

From the official instructions: docs.docsgpt.cloud/Deploying/Docker-Deploying. Always check the source for the current version before you run it.

Known gotchas when self-hosting DocsGPT

• A fresh install has no sign-in; every visitor is the single user "local" and shares its conversations, sources and connected services. Use AUTH_TYPE=oidc for any install that several people use or that faces the internet. source
• The simple_jwt and session_jwt auth modes use tokens that do not expire and cannot be revoked one by one; apart from a single-user install with LOCAL_MODE_ADMIN, only oidc supports admins, so the admin dashboard and usage quotas need oidc. source
• Do not generate a new ENCRYPTION_SECRET_KEY over an existing one without keeping the old value in ENCRYPTION_SECRET_KEY_PREVIOUS; stored credentials would become unreadable. source
• Data lives in named Docker volumes; docker compose down keeps it, but down -v removes it. source

Alternatives in Knowledge base & RAG

• RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare DocsGPT vs RAGFlow
• AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs DocsGPT
• PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare DocsGPT vs PrivateGPT
• Open Notebook Private, self-hosted alternative to Google NotebookLM with your choice of AI models. Compare DocsGPT vs Open Notebook
• Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare DocsGPT vs Onyx (formerly Danswer)
• FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare DocsGPT vs FastGPT
• kotaemon Open-source RAG web app for chatting with your documents, with citations and GraphRAG. Compare DocsGPT vs kotaemon
• MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare DocsGPT vs MaxKB

Sources

• GitHub repository: github.com/arc53/DocsGPT
• Official documentation: docs.docsgpt.cloud/
• License text: github.com/arc53/DocsGPT/blob/main/LICENSE
• Hardware requirements, Deploy instructions, Gotcha 4: docs.docsgpt.cloud/Deploying/Docker-Deploying
• Gotcha 1, Gotcha 2, Gotcha 3: docs.docsgpt.cloud/Deploying/Security
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 24, 2026