Claude Code’s auto memory writes project notes to disk and loads only the first 200 lines
thisdudelikesAI · x · 2026-07-23
The post explains Claude Code’s auto-memory system:
- Auto memory is on by default.
- Claude writes notes to /.claude/projects/<project>/memory/ as it works, including build commands, bugs, and user corrections.
- Only the first 200 lines of MEMORY.md are loaded each session; the rest lives in topic files and is loaded on demand.
The point is that memory is incremental and session loading is limited, so structure matters.
Related event: Best Practices for Claude Code Memory and Rules(12 posts)→
More from coding & agent
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11