How GBrain Works, and How to Actually Wire It Into Your Agents
Source
AlphaSignal
Author
AlphaSignal
Date
Key takeaways · AI-distilled
Every page uses a compiled-truth-plus-timeline split. Above the divider sits the current best understanding, rewritten when evidence changes it; below sits an append-only evidence trail that is never edited, only extended.
Enrichment is tiered by attentionThe mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.Full definition → rather than manual tagging: one mention gets a stub page, three mentions across different sources trigger web and social lookup, and a meeting or eight-plus mentions runs the full pipeline.
Dropping the intent classifier costs 63.2% source accuracy, because boosting compiled-truth chunks ranks assessments above timeline entries even when the question asks for a date. Classifying the query first is what makes the boost safe.
The published retrieval numbers come from a 29-page synthetic corpus while the production brain is 17,888 pages, and performance at that scale has never been benchmarked publicly. Read them as design signal, not a scale claim.
The CLI and the MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → server are both generated from one contract-first interface of about 30 shared operations, so the two surfaces cannot drift apart, and the 25 skills stay plain markdown you edit without touching compiled code.
Terms in this piece · Glossary
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Why it matters
A teardown of Garry Tan's open-sourced production knowledge infrastructure — 17k+ pages, thousands of dossiers — and how to wire that pattern into your own agents. Concrete architecture from a real, large deployment.
Key quotes
“intent classifier: 87% deterministic, up from 40% in week 1.”
