This page outlines how developers can connect to and utilize Brainery's extensive knowledge base and AI-driven capabilities. By integrating a straightforward MCP configuration, you can seamlessly access powerful insights directly within your existing development tools and workflows.

Access the brainery

We ran memo.d.foundation through is-agentic.com, read its rubric closely, and shipped the fixes that took the score from 50 to 93. Here is the rubric in full and what each fix actually did.

Making our site AI-agent-ready, 50 to 93

An overview of Brainery's architecture, detailing how it ingests, processes, and transforms data from diverse sources into a dynamic knowledge base.

Brainery architecture

Implementing a Golang-based visualization for crypto market performance indicators, focusing on Bitcoin vs Altcoin dynamics and trading strategy effectiveness through interactive charts and data analysis

Visualizing crypto market performance: BTC-Alt dynamic indicators in Golang

How data flows through Brainery's second brain system, from Discord, Memo Blog, and GitHub sources to TimescaleDB via MCP, with an LLM-powered interface for natural language queries.

Data flow in Brainery

A migration-less, append-only database design using TimescaleDB's hypertables and continuous aggregates to capture observational data and detect emerging patterns through LLM analysis.

Database design and philosophy

Memo now picks the related notes Ask reads beside each article from a 522-note bge-m3 index instead of the folder a note sits in. The same index lost a blind 40-question eval for the web chat, so chat keeps its topic table for now.

Related notes by meaning: an embedding index won memo's Ask and lost the chat eval

Explore how we solved the catastrophic forgetting problem in LLMs by building an external knowledge system that mimics learning through context manipulation, without touching the model's parameters.

Build a brain that never forgets

This post explains the multi-stage process of transforming raw data into structured information, and then synthesizing that information into persistent insight and knowledge within a true second brain, leveraging tools like TimescaleDB and LLMs.

Promoting raw data to insight

A Request for Comments (RFC) detailing a comprehensive specification for implementing OAuth 2.1 authorization within the Model Context Protocol (MCP) when using Server-Sent Events (SSE) as the transport mechanism, ensuring vendor-neutral security for AI-to-tool communication.

MCP authorization over SSE

RFC proposing a novel approach to track concept evolution using TimescaleDB with pgvector/pgvectorscale, enabling historical semantic analysis and preventing catastrophic forgetting in continual learning systems.

Append-only concept embedding log

Building systems that actually learn and get smarter over time is hard, facing challenges with traditional databases and LLMs. This post outlines an approach to building a true second brain that continuously learns, generates insight, and remembers it through an append-only log and flexible data structures.

Reports > Experiment

2026

October (1 posts)

August (1 posts)

2025

May (9 posts)

2024

November (1 posts)