Incremental Indexing Python Packages

loci-rag

A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

codenib

Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.

smritikosh

Semantic vector search over a codebase

markdown-fastrag-mcp

Fast markdown RAG with multi-provider embeddings (Vertex AI, Gemini, OpenAI, Voyage), incremental indexing with mtime/size fast-path, stale vector pruning, Milvus vector store.

steadlith

Steadlith reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.

cairn-rag

Steadlith reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.