repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · yesterday
vitali87/code-graph-rag
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Dataset of permissively licensed code released →
- PossiblePossibly related (embedding) · 50%IEEE Rolls Out Large Language Models Virtual Training Course →
- PossiblePossibly related (embedding) · 50%KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers →
- PossiblePossibly related (embedding) · 49%DeepSWE: new benchmark looking at how well today's frontier models can actually write code [R] →
- PossiblePossibly related (embedding) · 47%EU Backs Open-Source AI Model Covering 24 EU Languages - Slator →
- PossiblePossibly related (embedding) · 47%Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization →
- PossiblePossibly related (embedding) · 48%Setting Up Your Own Large Language Model - Towards Data Science →
- PossiblePossibly related (embedding) · 49%ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation →
Covers
Implements
Implements (incoming)
Covers (incoming)
Related across the graph
paperObject Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt OptimizationnewsSetting Up Your Own Large Language Model - Towards Data SciencenewsEU Backs Open-Source AI Model Covering 24 EU Languages - SlatornewsDataset of permissively licensed code releasedpaperProjAgent: Procedural Similarity Retrieval for Repository-Level Code GenerationnewsIEEE Rolls Out Large Language Models Virtual Training CoursepaperKnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in TransformersnewsDeepSWE: new benchmark looking at how well today's frontier models can actually write code [R]