We curate open-source GitHub repositories matching “semantic code search llm”. Results are ranked by relevance to your query — pick filters below to narrow, or refine with AI.
Bloop is an AI code analysis tool and semantic search engine designed for understanding and querying large-scale codebases. It utilizes a high-performance indexing system written in Rust to enable fast symbol and text retrieval across multiple programming languages. The project differentiates itself by using on-device embeddings for semantic code search, allowing users to locate logic based on meaning and intent rather than exact keywords. It combines a language model with a retrieval-augmented generation approach to provide a natural language interface for conversational querying and the gen
Bloop is a dedicated semantic code search engine that indexes multi-language codebases and uses an LLM with retrieval-augmented generation to answer natural language queries about code, directly matching the intent.
LEANN is a framework for local retrieval augmented generation and vector indexing. It functions as a system for building local knowledge bases and source code search engines that combine large language models with retrieved private data to generate context-aware responses. The project distinguishes itself through a vision-model based document layout extractor for parsing complex PDF figures and diagrams, and a source code search engine that employs structure-aware chunking to preserve function and class boundaries. It also implements the Model Context Protocol to integrate real-time data sour
LEANN is a local RAG framework explicitly designed for building source code search engines with structure-aware chunking and LLM-based retrieval, directly matching the need for a semantic code search tool that supports natural language queries over code.
Sourcegraph is a full-featured open-source code search platform that incorporates LLM-powered semantic search via its Cody AI assistant, supporting natural language queries, code embeddings, multi-language indexing, and retrieval-augmented generation, making it a comprehensive solution for this search.