An engram is a living knowledge base that organizes itself. Feed it sources - URLs, papers, notes - or sync from GitHub, Notion, and more. It compiles everything into a knowledge graph and wiki, maintained entirely by AI. Every question you ask makes it smarter. Background agents tend to it while you sleep, refreshing information and discovering knowledge gaps. Obsidian and Notion make you the librarian. Engrams makes you the researcher.
Hey everyone! I'm a freshman in college interested in computational cognitive science and AI research. I'm fascinated by intelligence of all forms, and recently saw Karpathy's tweet about using LLMs to compile personal knowledge bases, i.e., a second brain. I've been thinking of ways to externalize cognition for a while, and this tweet really solidified the vision for engrams: knowledge that organizes itself. A living structure that reads what you read, finds gaps you can't find, and compounds every time you interact with it.
That's what I built. You feed it anything, and it compiles structured knowledge. Features include a knowledge graph representing concepts and relations as nodes and edges, a comprehensive, indexable wiki, and autonomous agents that tend the engram and serve as units of cognition.
Core loop is live and working. Background agents, browser extension, service integrations, and team collaboration are actively shipping. Try it out with a topic you know inside out, whether it be research or coffee.
EAGER TO HEAR THOUGHTS AND FEEDBACK!!!
