# GraphStaff

> GraphStaff is an AI knowledge platform for developer documentation, customer knowledge hubs, and a permission-aware Company Brain. It gives people and AI agents grounded answers from one governed knowledge graph.

Canonical site: https://graphstaff.ai/

Full consolidated context: https://graphstaff.ai/llms-full.txt

## Overview

- [AI Knowledge Platform | GraphStaff](https://graphstaff.ai/): GraphStaff is an AI knowledge platform for developer docs, customer knowledge hubs, and company knowledge, with governed answers for people and AI agents.

## Products

- [Developer Docs and API Docs | GraphStaff](https://graphstaff.ai/developer-docs/): Developer documentation and API references for humans and AI agents, with grounded Ask AI, automatic MCP, llms.txt, and Markdown pages.
- [Customer Knowledge Hubs | GraphStaff](https://graphstaff.ai/knowledge-hubs/): Branded, searchable customer knowledge hubs with grounded Ask AI, audience controls, and clear support escalation.
- [Company Brain | GraphStaff](https://graphstaff.ai/company-brain/): A permission-aware Company Brain that gives Claude, ChatGPT, coding agents, and your AI infrastructure consistent company context through MCP.
- [Graph-Based Knowledge Retrieval | GraphStaff](https://graphstaff.ai/our-secret-sauce/): How GraphStaff's proprietary graph-based knowledge retrieval engine follows relationships to assemble complete, permission-aware context.

## Pricing

- [Pricing | GraphStaff](https://graphstaff.ai/pricing/): GraphStaff pricing. Docs and Knowledge Hubs for $500 per month with everything included, and Company Brain starting at $80k per year with dedicated onboarding.

## Solutions

- [GraphStaff for Support Teams | GraphStaff](https://graphstaff.ai/solutions/support-teams/): A branded customer knowledge hub with grounded, cited Ask AI, audience controls, and clean escalation into your existing help desk.
- [GraphStaff for API Teams | GraphStaff](https://graphstaff.ai/solutions/api-teams/): OpenAPI in, living reference out: synthesized examples, three-language samples, a safe try-it playground, and AI agent surfaces that respect permissions.
- [GraphStaff for Technical Writers | GraphStaff](https://graphstaff.ai/solutions/technical-writers/): One MDX source in git becomes the website, the search index, the AI answers, and the AI agent surfaces, with permissions intact on each.
- [GraphStaff for AI Platform Teams | GraphStaff](https://graphstaff.ai/solutions/ai-platform-teams/): One governed MCP gateway feeds Claude, ChatGPT, coding agents, and your own AI infrastructure the same permission-aware knowledge.

## Comparisons

- [Mintlify vs GitBook vs GraphStaff | GraphStaff](https://graphstaff.ai/compare/mintlify-vs-gitbook/): Compare Mintlify, GitBook, and GraphStaff across authoring, permissions, AI-agent access, retrieval, and pricing.
- [Confluence vs Notion vs GraphStaff | GraphStaff](https://graphstaff.ai/compare/confluence-vs-notion/): Compare Confluence, Notion, and GraphStaff for team knowledge, permissions, AI access, grounded answers, and pricing.

## Research

- [Graph-Based AI Research | GraphStaff](https://graphstaff.ai/ai-research/): GraphStaff research on connected, permission-aware memory, graph-based retrieval, and grounded context for AI agents.

## Blog

- [Blog | GraphStaff](https://graphstaff.ai/blog/): Articles and guides from GraphStaff on grounded AI answers, developer docs, knowledge hubs, and making company knowledge work for people and AI agents.
- [Introducing GraphStaff | GraphStaff](https://graphstaff.ai/blog/introducing-graphstaff/): One governed knowledge graph that answers customers, developers, employees, and their AI agents, with grounded and cited responses on every surface.
- [Retrieval that follows the connections | GraphStaff](https://graphstaff.ai/blog/retrieval-that-follows-the-connections/): Why GraphStaff retrieves knowledge by walking a governed graph of pages, concepts, and policies instead of ranking isolated text chunks.
- [Your knowledge has a second audience now | GraphStaff](https://graphstaff.ai/blog/your-knowledge-has-a-second-audience/): AI agents read your documentation too. How GraphStaff serves MCP, llms.txt, and Markdown so agents answer from your maintained content instead of guessing.


## Usage notes

- Prefer the canonical URLs listed in this file when citing GraphStaff.
- Product capabilities and prices should be verified against the linked page because the website is the current source of truth.
- This file is generated from the production HTML during every build.