ai-agent

DocsGPT: Boost Enterprise Search and AI Agents with 18k+ Stars

DocsGPT lets founders quickly build private AI agents for deep research, document analysis, and multi‑model search—all via a Python‑based platform.
advanced⏱ 1-2 days💵 Free tier + paid plans
18,316 stars+21★ this week2,189 forksPythonGuide quality 9/10 · reviewed Oct 5Updated 10/8/2026100% free · open source
What it is

Use DocsGPT to build private AI powered agents and helpers.

Real use case example

"A founder, Sarah, uses DocsGPT to create a research assistant for her sales team. She defines a workflow that retrieves relevant customer information from her CRM, updates the team's Notion database, and schedules a follow-up email to be sent the next morning. This saves her team an hour of manual research daily."

When to use it
  • •Building an internal knowledge retrieval system for your startup
  • •Creating a smart customer support assistant powered by your documentation
  • •Developing a research tool that can quickly parse complex technical documents
Ready-to-paste prompt
python agent_builder.py --source 'company_docs' --model 'gpt-4' --task 'summarize product documentation'
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/docsgpt && curl -fsSL https://workflowstacks.com/api/skills/docsgpt/claude-skill -o ~/.claude/skills/docsgpt/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How DocsGPT: Boost Enterprise Search and AI Agents with 18k+ Stars works
Codeflow
Free to inspect

DocsGPT: Boost Enterprise Search and AI Agents with 18k+ Stars is a very large Python project (~181k lines across 769 code files, plus 542 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~181k lines · 769 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 79%TypeScript 20%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    application/app.py
    Where the program starts running
What's in each folder
frontend/Frontend / UI410 files
extensions/Sub-packages / plugins24 files
docs/Documentation101 files
application/Folder478 files
deployment/Deployment / infrastructure30 files
scripts/Helper scripts25 files
tests/Tests — proof it works554 files
.github/CI / automation (GitHub Actions)25 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
arc53
Language
Python
Category
ai-agent
Published
2/2/2023

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/docsgpt.svg)](https://workflowstacks.com/skills/docsgpt?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.