[GitHub Trending] Graphify-Labs/graphify
8.4 relevance
Score Breakdown
technical depth 8
novelty 9
actionability 9
community 8
strategic 6
personal 10
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
AI coding assistant skill to query code and data, highly relevant and novel.
Summary
Graphify-Labs/graphify uses tree-sitter AST to build a deterministic, local-first knowledge graph from code, docs, and media, queryable via /graphify in AI assistants like Claude Code and Cursor. Every edge carries EXTRACTED or INFERRED confidence tags, and the graph supports query, path, and explain commands without embeddings or vector stores. Benchmarks on LOCOMO and LongMemEval show it achieves 0.497 recall@10 and 76% QA accuracy, outperforming mem0 and supermemory while using zero LLM credits for code parsing.
Author
Graphify-Labs