Context That Compounds: What I Learned Building a Memory Lifecycle for Coding Agents By Edouard Maleix Most teams manage agent context with static rule files — CLAUDE.md, AGENTS.md, custom YAML checklists, skills, etc. I do too. Then I tracked what actually happened: agents repeated the same mistakes across sessions, rules accumulated without evidence they helped, and review load stayed constant no matter how many rules I added.Attribution — when an agent opens a PR, you can't tell what it wrote, why, or whether a human reviewed it. Giving agents their own signing keys and git identity changes code review from guessing to auditing.Memory that persists — Monday you correct an agent, Tuesday it makes the same mistake. I built a typed diary (episodic, procedural, semantic, reflection entries) that survives across sessions and compiles into token-budget context packs. The difference vs. static rules: rules authored from memory can't compound; entries harvested from incidents can.Evaluating context, not just code — SWE-bench tests whether agents can fix bugs. I needed something different: does this context pack actually help the agent avoid known mistakes? I'll show why scenarios harvested from real incidents (20–67% baseline → 95–100% with context) wildly outperform auto-generated ones.
