RAG & Knowledge
linkly-ai-skills
Skills that let coding agents search and read your local documents.
★ 65 starsApache-2.0
View guide →LibreAI / RAG & Knowledge / DocsGPT
// rag · arc53/DocsGPT
DocsGPT
DocsGPT is an open-source rag & knowledge project by arc53 (arc53/DocsGPT on GitHub). It has 18,316 GitHub stars and 2,189 forks, is released under the MIT license, and was last updated on GitHub on 8 October 2026.
A private AI platform for agents, assistants and enterprise search over your documents
★ 18.3k stars⑂ 2.2k forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- arc53/DocsGPT
- GitHub stars
- 18,316
- Forks
- 2,189
- License
- MIT
- Last updated on GitHub
- 8 October 2026
- Category
- RAG & Knowledge
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Gather your knowledge sources
Decide which documents or connected services the assistant should answer from.
- Get DocsGPT
Use the one-command installer, or clone the repo for Docker Compose or source deployment.
- Configure models and sources
Connect your model provider (or a local model) and sync your first knowledge source.
- Build your first agent
Create an agent with its own prompt, knowledge and tools, and ask it a question with sources.
// features
Why people love it
Agents with deep research
Agents have their own prompt, knowledge, tools and model, plus a research mode for multi-step answers.
Visual workflow builder
Chain agents, conditions, state and sandboxed code in a drag-and-drop builder.
Knowledge from anywhere
Ingests PDFs, Office files, web pages and audio, kept in sync from Drive, SharePoint, Confluence, GitHub, S3 and more, with GraphRAG.
Answers with sources
Every answer cites the documents it came from, so users can verify.
Tools, actions and guardrails
Web search, REST APIs, MCP servers and sandboxed code as tools; guardrails flag or block PII, secrets and prompt injection.
Any model
Use OpenAI, Anthropic, Google, Groq, OpenRouter, or local models via Ollama, vLLM and other OpenAI-compatible servers.
Advertisement
// run it
Run it yourself
- Clone the repository
Get the source code from GitHub and enter the project directory.
git clone https://github.com/arc53/DocsGPT.git cd DocsGPT - Install in one command
The README's quickstart uses the project's installer script to set up the stack.
# Run the one-command install from the README quickstart - Manage the stack
After install, the docsgpt command manages status, logs, upgrades and backups.
docsgpt status docsgpt logs docsgpt upgrade
// use cases
What you can build
- Build a support assistant that answers only from your product docs, with citations
- Give a team enterprise search across Drive, Confluence and GitHub content
- Automate a weekly research brief with the deep-research mode and schedules
- Deploy a private ChatGPT alternative for a regulated team using local models
Advertisement
// faq
Questions, answered
Who maintains this project?
It is maintained by arc53 and contributors on GitHub; a hosted cloud version is offered at app.docsgpt.cloud.
Is it free to use?
Yes - DocsGPT is MIT licensed and free to self-host. The hosted cloud is a separate service.
Does it need a paid API key?
You bring a model: cloud providers need your API keys, or you can run fully local models through Ollama or vLLM at no per-token cost.
How does it compare to alternatives?
Compared with plain RAG frameworks like LlamaIndex, DocsGPT is a complete private platform - agent builder, workflows, connectors, guardrails and UI - rather than a library you assemble yourself.
How do I get started?
Run the one-command install from the README, connect a model and one knowledge source, and build your first agent in the UI.
// keep exploring
Similar tools
RAG & Knowledge
Utopia
Utopia — an open-source enterprise world model: a bitemporal knowledge substrate that learns from your documents and gives agents a governed, auditable memory
★ 8.4k starsApache-2.0
View guide →RAG & Knowledge
LEANN
The smallest vector index in the world: private RAG over everything on your laptop with 97% less storage.
★ 13.0k starsMIT
View guide →RAG & Knowledge
pipeshub-ai
The open-source, permission-aware context layer that lets agents search all your company knowledge.
★ 3.8k starsApache-2.0
View guide →RAG & Knowledge
deep-searcher
DeepSearcher — open-source deep research over your private data, with reasoning models and Milvus retrieval.
★ 8.3k starsApache-2.0
View guide →RAG & Knowledge
vespa
Vespa — the AI search platform: vector, text and tensor search at production scale.
★ 7.1k starsApache-2.0
View guide →// alternatives
Alternatives in RAG & Knowledge
The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if DocsGPT is not the right fit.
- MarkItDown★ 193.5k
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
- Dify★ 157.8k
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
- MinerU★ 82.5k
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
// more in rag
More in RAG & Knowledge
Nearby RAG & Knowledge projects in the catalogue, closest in stars to DocsGPT — keep exploring the shelf either side of it.
- DB-GPT★ 20.1k
An agentic AI data assistant - chat with your databases, run SQL and code, get reports
- turbovec★ 17.4k
A blazing-fast vector index in Rust, built on TurboQuant - with Python bindings
- pgvector★ 23.3k
Vector similarity search inside Postgres - store embeddings next to your data
- SurfSense★ 16.3k
Air-gapped, open-source NotebookLM alternative that turns local documents into briefings, decks and podcasts.
- opendataloader-pdf★ 29.5k
Turn PDFs into AI-ready data: extract Markdown, JSON and tables — and auto-tag for accessibility
- zvec★ 16.1k
Lightweight, lightning-fast in-process vector database from Alibaba that embeds in your app.
Get DocsGPT
Free and open — grab the source, star the repo, and start creating.