Seven Coding Agents. One Chat Window.
Building lasteverLM in 78 hours with a head agent, a Linux VM and 20–24 hours of my own time — and what I want from fleet tooling next.

Building lasteverLM in 78 hours with a head agent, a Linux VM and 20–24 hours of my own time — and what I want from fleet tooling next.

Four tools called agent memory. Four different approaches to what should survive. One puts decision rationale next to the code.

Rationale, structured knowledge, or codebase intelligence for coding agents?

Decisions that cite each other across repositories — no graph database, no central index, no account. Just Markdown and Git.

Install it, initialize the project, keep coding.
