khanhtq29vn /
contextcraft
AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs
Updated 16 min ago
Why now
Version v0.4.0 came out on November 1.
+11 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
A Python tool that compresses a codebase into a token-budgeted, AST-aware summary for LLM prompts, ranking files by dependency centrality. Aimed at developers feeding repositories to coding agents or RAG pipelines.
Summary written by AI from the repository’s description and README.
khanhtq29vn / contextcraft
View on GitHub(opens in new tab)