Recursive Chunking
Break large files into manageable chunks and process them recursively with sub-LLM calls for comprehensive analysis.
rlm-rs
Recursive Language Model REPL for Claude Code — long-context tasks via chunking and recursive sub-LLM calls
Hybrid Search
Combines BM25 text search with vector similarity using Reciprocal Rank Fusion for precise context retrieval.
Embedded Embeddings
Ships with BGE-M3 model via fastembed — no external API calls needed for vector operations.
Claude Code Plugin
Integrates as a Claude Code skill for seamless use within your existing AI-assisted development workflow.