Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python aicode-complexitycode-healthcode-intelligencecode-qualitydead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-sourcepythonrefactoringstatic-analysistechnical-debt
Fix/minor (#60)
Swati Ahujac239c1544108
diff --git a/README.md b/README.mdindex d8116ab04..bf1b62916 100644--- a/README.md+++ b/README.md@@ -29,6 +29,23 @@ The result: Claude Code answers *"why does auth work this way?"* instead of *"he---+## π Benchmarked against frontier LLMs++> **[repowise-bench β](https://github.com/repowise-dev/repowise-bench)** β an open SWE-QA benchmark that grades how well standard LLMs answer real software-engineering questions over real repositories.+>+> On 48 paired tasks from `pallets/flask` (`claude-sonnet-4-6`, end-to-end), repowise-augmented Claude Code matches baseline answer quality while being dramatically leaner:+>+> | Metric (per task, mean) | Baseline | **+ repowise** | Ξ |+> |---|---|---|---|+> | π° Cost | $0.1396 | **$0.0890** | **β36 %** |+> | β‘ Wall time | 41.7 s | **33.9 s** | **β19 %** |+> | π οΈ Tool calls | 7.4 | **3.8** | **β49 %** |+> | π Files read | 1.9 | **0.2** | **β89 %** |+>+> **32 / 48 (67 %)** tasks are cheaper with repowise β at parity quality (judge Ξ β β0.01).++---+## What's new### Faster indexing