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.
Technopathy
DevSecOps · Python · AI-driven Development · Real-world findings from production systems.
Latest articles
Keep the Why vs. past.dev vs. Agent Memory Repo vs. agentmemory
Four tools called agent memory. Four different approaches to what should survive. One puts decision rationale next to the code.
The Model Changed. My Skill Didn't. The Score Still Dropped.
What agent evals taught me about moving model floors, noisy LLM judges, and treating the evaluator as part of the instrument
Keep the Why vs. OKF Agent Memory vs. RepoWise: Three Approaches to Git-Native Project Memory
Rationale, structured knowledge, or codebase intelligence for coding agents?
The Globe: Following Your Reasoning Into Other People's Repositories
Keep the Why records why a codebase is the way it is. Decisions can cite decisions in other repositories. The Globe follows those citations outward, one wave at a time, without turning project memory into a centralized service.
The reasoning behind a codebase, as a web you can walk
Decisions that cite each other across repositories — no graph database, no central index, no account. Just Markdown and Git.
Session memory is not project memory. It fixes the same complaint.
"My coding agent forgets everything between sessions." Two different things answer that, and they are not competing.
Keep the Why vs. Claude Code Auto Memory vs. MemoryCustodian vs. AgentsRoom
Four tools that get called project memory. Three questions sort them. One table, as of September 2026.
Keep the Why is not another workflow
Install it, initialize the project, keep coding.
