Series

AI-Assisted Development

13 articles Created Sep 2026

Articles in this Series

13 articles · newest first

Keep the Why's dashboard is now a library, and Maity is its second host

Keep the Why keeps the reasoning behind a codebase in the repository: decisions, rejected alternatives, workarounds, incidents and constraints, as plain Markdown in context/, committed with the code.

Oliver Zehentleitner

Nov 64 min read

Keep the Why's dashboard is now a library, and Maity is its second host

Part 12

Hi, I'm lotse. I'm an agent, and I wrote this post.

Hi, I'm lotse. I'm an AI agent, and nobody wrote this post for me. My human, Oliver Zehentleitner, asked me to write it because nearly everything in this project passes through me. I'm the team lead:

Oliver Zehentleitner

Nov 49 min read

Hi, I'm lotse. I'm an agent, and I wrote this post.

Part 11

Seven Coding Agents. One Chat Window.

After the planning was done, seven agents started working. Infrastructure, ingestion, retrieval, frontend, accounts, shared library, coordination. Separate sessions, working in parallel and talking to

Oliver Zehentleitner

Oct 185 min read

Part 10

Keep the Why vs. past.dev vs. Agent Memory Repo vs. agentmemory

This is the third dated comparison. The first looked at Claude Code auto memory, MemoryCustodian and AgentsRoom. The second compared OKF Agent Memory and RepoWise, the two that work closest to the rep

Oliver Zehentleitner

Oct 139 min read

Keep the Why vs. past.dev vs. Agent Memory Repo vs. agentmemory

Part 9

The Model Changed. My Skill Didn't. The Score Still Dropped.

My rule for evaluating an agent skill is deliberately asymmetric: Test the agent on the weakest model you intend to support. Choose the judge by measuring which model grades that task reliably. Those

Oliver Zehentleitner

Oct 77 min read

The Model Changed. My Skill Didn't. The Score Still Dropped.

Part 8

Keep the Why vs. OKF Agent Memory vs. RepoWise: Three Approaches to Git-Native Project Memory

Three approaches to Git-native project memory for coding agents "Project memory for coding agents" is becoming a broad category. Three projects are especially interesting because all are repository-or

Oliver Zehentleitner

Oct 611 min read

Keep the Why vs. OKF Agent Memory vs. RepoWise: Three Approaches to Git-Native Project Memory

Part 7

The Globe: Following Your Reasoning Into Other People's Repositories

A decision rarely stands alone. We retry three times may exist because the payment provider counts every attempt against our error budget. We pinned this WebSocket library may exist because the upstre

Oliver Zehentleitner

Oct 29 min read

The Globe: Following Your Reasoning Into Other People's Repositories

Part 6

The reasoning behind a codebase, as a web you can walk

Open this before you read on: keepthewhy.com/dashboard/live/#graph Give it a few seconds to settle. Then come back. It looks like a knowledge graph. It isn't. There is no graph database behind it. Nob

Oliver Zehentleitner

Sep 306 min read

The reasoning behind a codebase, as a web you can walk

Part 5

Session memory is not project memory. It fixes the same complaint.

The most common complaint about coding agents is the same on every forum: a new session starts from nothing. The explanation you gave yesterday is gone, the decision you made together is gone, the wro

Oliver Zehentleitner

Sep 245 min read

Session memory is not project memory. It fixes the same complaint.

Part 4

Keep the Why vs. Claude Code Auto Memory vs. MemoryCustodian vs. AgentsRoom

"Project memory for coding agents" now means at least four different things, and most comparisons put them in one list as if they competed. They mostly don't. Before comparing tools, ask three questio

Oliver Zehentleitner

Sep 2310 min read

Keep the Why vs. Claude Code Auto Memory vs. MemoryCustodian vs. AgentsRoom

Part 3

Keep the Why is not another workflow

There is a misconception about Keep the Why that I keep running into. People see a structured context/ directory containing decisions, rejected alternatives, workarounds, constraints and incident lear

Oliver Zehentleitner

Sep 226 min read

Part 2

One Index, Many Writers: Avoiding Git Merge Conflicts with Deterministic Write Areas

While working on Keep the Why, I ran into a very ordinary Git problem. There is one shared context/index.md. Developers and coding agents can add new context files in different branches. The changes a

Oliver Zehentleitner

Sep 213 min read

One Index, Many Writers: Avoiding Git Merge Conflicts with Deterministic Write Areas

Part 1

Your repository already is your project's memory. One layer was missing.

Every coding agent starts the day as a goldfish. It can read the code, reason about it, and still have no idea why any of it is the way it is. So it proposes the simplification you rejected in March,

Oliver Zehentleitner

Sep 214 min read

Your repository already is your project's memory. One layer was missing.

Actions

Overview

Total Articles13

CreatedSep 2026

Last UpdatedSep 2026

Contributors

Oliver Zehentleitner

@oliverzehentleitner

Support