Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
TypeScript ai-agentsanthropicclaude-codeclicode-graphcodexcontext-engineeringcursordeveloper-toolsgeminiknowledge-graphllmmcpmcp-serveropen-sourceopenaitree-sitter
docs: move the 'vs. standard session' caption below the metrics table
Shrish Dwivedi4a61c664e973
diff --git a/README.md b/README.mdindex b58a6386..eb86b472 100644--- a/README.md+++ b/README.md@@ -15,8 +15,6 @@<!-- numbers from a 162-run benchmark (2026-07-22, 2 repos, 3 arms) — see Benchmark below -->-**vs. a standard coding session, no Graft at all:**-| Metric | With Graft ||---|---|| Cost | **32% less** |@@ -24,6 +22,8 @@| Latency | **60% lower** || Correctness | equal |+**vs. a standard coding session, no Graft at all.**+</div><p align="center">