Blog
The Unabyss Vault
Everything we know about personal context for AI - what it is, how it works, how to build it, and why the difference between context and memory matters more than it sounds. Written for people who use AI tools seriously and want to get more out of them.
Read article Featured
juggling three balls but i never learned how to juggle... so we made a formula instead
Where AI value actually comes from - and why we picked context
AI value = competence x execution, all to the power of context. Most builders try to solve all three at once and faceplant from zero focus. We picked context and are building the default infra for it.
27 May 2026 · 2 min read
Read article Manifesto
AI without context is like a brilliant person with amnesia asking who are you a thousand times. We are building how to gather context, make AI understand it, and do it fast and seamlessly.
11 June 2026 · 1 min read
Read article Personal RAG vs Context Files vs a Context Layer: Which Do You Actually Need?
If you want AI to work from your knowledge and your context, you've probably run into three approaches: build a personal RAG system, write context files, or use a context layer. They get discussed ...
10 June 2026 · 4 min read
Read article How to Connect an LLM with MCP
MCP — the Model Context Protocol — has become the standard way to connect AI tools to outside data and services. If you've set up an MCP server before, you've probably connected an LLM to a databas...
7 June 2026 · 3 min read
Read article What Is Karpathy's LLM Wiki?
An LLM Wiki is a folder of plain Markdown files that an AI agent builds and maintains as structured topical knowledge - complementary to personal context about who you are.
6 June 2026 · 4 min read
abyss — from Latin abyssus: chaos, the bottomless, the immeasurable. un- — the opposite of. Unabyss — structure, order, clarity.
The universal context layer for AI tools. Your data. Your rules. You decide who sees what. Structured once. Shared on your terms.
Unabyss-0.9.0