LOT 002 · AI Memory Layer · In Development
MAYNFRME
The AI memory layer for modern businesses.Companies spend millions on AI tools but every interaction starts from zero. There's no canonical memory layer — no place where the company's accumulated context, decisions, projects, and people-knowledge lives in a way every agent and human can use.
The case
Why MAYNFRME
Our thesis
The companies that win the next decade will own a memory layer their AI agents query — not a documentation system humans pretend to keep updated.
What it is
MAYNFRME is an AI operating system for the company: project state, agent state, knowledge state, and operator commands — composable, queryable, and owned by the business.
Under the hood
How it's built
Cloudflare Workers + Neon + Cloudflare R2 for embeddings cache. Self-host option for enterprise tier.
Stack
- Next.js + Postgres with pgvector for embedded retrieval
- Agent runtime supporting OpenAI, Anthropic, and local models
- Structured event log — every decision becomes part of the memory
- Composable commands that orchestrate agents across projects, ops, and growth
- Identity + ACL layer so agents only see what they're authorized to see
Approach
- 01Start with the memory model: events, projects, people, artifacts, decisions.
- 02Build retrieval before generation. The reasoning is downstream of what the system can recall.
- 03Treat agents as composable workers, not chat interfaces.
- 04Design for the swap: every model is replaceable behind a single contract.
The goal
Become the canonical operating layer modern companies run their AI on — vendor-agnostic, owned, compounding.
Next step
Want this kind of system inside your business?
We take two Blueprint Sprints a month. Rodrigo reads every application and replies within two business days.