Open-source Graft fights coding agent amnesia with markdown, claims SWE-bench win over Claude Code

thisdudelikesAI · x · 2026-09-07

An open-source project called Graft tackles a core coding-agent pain point: agents rebuild their understanding of a codebase from scratch every session—grepping, opening files, following imports—throwing away what they mapped an hour ago.

How Graft works:

The author claims Graft beat Claude Code on SWE-bench Verified (real GitHub issues with maintainers' tests)—a single-party claim pending independent verification. Still, the file-based, zero-infrastructure memory approach is an interesting pattern for agent engineering.

Original post →

More from coding & agent

coding & agent channel →