oooscoos/Benzi

Most coding agents grep and glob raw source into LLM's context window and hope the model is smart. Benzi compiles your codebase into a map of calls, data flow, control flow and class hierarchy first, then reads, explains, runs, edits and verifies from it. 82.4% SWE-bench Verified pass@1 for < $13.

165
Stars
10
Forks
0.0
Radar Score
Declining
Momentum

Scoring Breakdown

Impact0.0
Velocity0.0
Health0.0

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
HTML

Why it ranks

Momentum is cooling relative to the rest of the index.

AI Coding Tools ยท ide extension
View on GitHub