Your repository already is your project's memory. README → what docs → how tests → expected behavior Git → what changed, when and by whom Coding agents exposed the missing layer: context/ → why Why the workaround exists. Why an approach was rejected. Why something that looks wrong is intentional. My argument: project memory doesn't need to begin with another database or service. Complete the structure we already have and keep the knowledge with the code. https://oliver-zehentleitner.github.io/repo-native-project-memory/ It's a thesis, not a product. Criticism very welcome. #AI #CodingAgents #SoftwareEngineering #DevTools #ContextEngineering #ProjectMemory #Git #OpenSource #LLM