Skip to content

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

docs(readme): add PR-review GitHub App badge + invite, drop the 162-run benchmark caption

Shrish Dwivedif23b358e076a
diff --git a/README.md b/README.md
index 028a3013..2a86ca4f 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,7 @@
<img src="https://img.shields.io/badge/License-MIT-20C997?style=for-the-badge" />
<a href="TELEMETRY.md"><img src="https://img.shields.io/badge/telemetry-anonymous%2C%20opt--out-546FFF?style=for-the-badge" /></a>
<a href="https://scorecard.dev/viewer/?uri=github.com/NanoNets/Graft"><img src="https://img.shields.io/ossf-scorecard/github.com/NanoNets/Graft?style=for-the-badge&label=openssf%20scorecard" /></a>
+ <a href="https://github.com/apps/trailhq-graft"><img src="https://img.shields.io/badge/PR%20reviews-install%20GitHub%20App-546FFF?style=for-the-badge&logo=github&logoColor=white" /></a>
</p>
### Up to **4× cheaper** and **3× faster**, with better or no loss of correctness.
@@ -26,14 +27,14 @@
| Time savings | Baseline | **+60%** |
| Correctness | 54% | **66% (+12 pts)** |
-<sub>Efficiency is a 162-run controlled benchmark (same agent, same file tools, only the context differs). Correctness is **SWE-bench Verified**, graded by the official harness — graft resolved 66% of instances tested against Cold Claude Code's 54%. [Efficiency method ↓](#benchmark) · [SWE-bench ↓](#swe-bench-verified) · [Per-repo numbers ↓](#tested-on-your-popular-repos)</sub>
-
</div>
<p align="center">
<img src="assets/graft-comparison-demo.gif" alt="Side-by-side comparison of a coding agent working with and without graft" width="820"/>
</p>
+> **Reviewing pull requests?** [Add the graft GitHub App](https://github.com/apps/trailhq-graft) to get an automatic blast-radius review on every PR.
+
---
## Contents