OOliver Zehentleitner·Nov 6Keep the Why's dashboard is now a library, and Maity is its second hostThe views that read a project's reasons (graph, timeline, thoughts, family) can now be mounted by any page. Maity shows them next to the board.5 min read·blog.technopathy.club2S
OOliver Zehentleitner·Oct 12Keep the Why vs. past.dev vs. Agent Memory Repo vs. agentmemoryFour tools called agent memory. Four different approaches to what should survive. One puts decision rationale next to the code.13 min read·blog.technopathy.club
OOliver Zehentleitner·Oct 5Keep the Why vs. OKF Agent Memory vs. RepoWise: Three Approaches to Git-Native Project MemoryRationale, structured knowledge, or codebase intelligence for coding agents?16 min read·blog.technopathy.club2A
OOliver Zehentleitner·Oct 5The 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 instrument9 min read·blog.technopathy.club
OOliver Zehentleitner·Sep 29The reasoning behind a codebase, as a web you can walkDecisions that cite each other across repositories — no graph database, no central index, no account. Just Markdown and Git.9 min read·blog.technopathy.club34JK
OOliver Zehentleitner·Sep 22Keep the Why vs. Claude Code Auto Memory vs. MemoryCustodian vs. AgentsRoomFour tools that get called project memory. Three questions sort them. One table, as of September 2026.13 min read·blog.technopathy.club917JEB
OOliver Zehentleitner·Sep 9One Index, Many Writers: Avoiding Git Merge Conflicts with Deterministic Write AreasHow a small structural change reduced unnecessary Git conflicts in a shared Markdown index — and made it easier for coding agents to navigate.4 min read·blog.technopathy.club24SM
OOliver Zehentleitner·Sep 8What happens when a coding agent forgets why a change was rejected?I tested what a fresh coding-agent session does when the repo remembers the code, but not the reasoning behind it.5 min read·blog.technopathy.club210JBS
OOliver Zehentleitner·Aug 24Same Skill, Six Agents, Nine Models: What a Real Eval Matrix Taught MeI ran the same skill and the same task through different coding agents. The model mattered. But the agent harness changed the outcome far more than I expected.15 min read·blog.technopathy.club2
OOliver Zehentleitner·Jul 28Keep the Why: Project Memory for Humans and AI AgentsHow a simple rationale-capture skill evolved into a repository-native knowledge lifecycle without a database, daemon, or dashboard.16 min read·blog.technopathy.club52N
