Build a knowledge graph from documents: a source-linked walkthrough
Build knowledge architecture that helps your AI agent find the right source, connect related facts and keep track of corrections.
Includes: Source-contract worksheet
Gigabrain / Guides
Knowledge that lasts.
Practical guides for building a knowledge system your AI agent can use.
Start here / Persistent memory
Persistent memory for AI agents: setup, sources and corrections
How to preserve project knowledge between agent sessions, retrieve source-linked facts and test corrections.
Read the guide 6 min read
Go deeper
An AI second brain needs more than storage
Put your notes to work with an AI agent. Build a second-brain workflow that keeps sources, corrections and permissions clear.
Includes: Weekly-review template
Use an Obsidian vault as agent knowledge
Use your Obsidian notes in an AI memory workflow. Start with a small project, check source citations and understand where your data goes.
Includes: Obsidian pilot checklist
Local vs hosted AI agent memory: privacy, costs and maintenance
Choose an AI memory setup that fits your work. Compare local control, hosted convenience, data access and what you will need to maintain.
Includes: Data-flow worksheet
What is RAG? Retrieval-augmented generation with a worked example
Follow a source from retrieval to an AI answer. Inspect a worked example, citation limits and a practical review worksheet.
Includes: Source-to-answer worksheet
What is GraphRAG? How relationships add context to retrieval
Trace a question across connected documents. Learn how graph retrieval works, what it can miss and how to review its evidence.
Includes: Relationship-path worksheet
The working library
Take something useful with you.
Practical templates to plan your knowledge system and check its answers. Download, adapt and use them with your own workflow.
Markdown files · No email requiredFrom ideas to practice
See the system behind the guides.
Inspect how Gigabrain stores, connects and retrieves your sources. Check your agent’s compatibility before choosing a plan.
Published by Gigabrain Labs
