MonkeyLLM vs MiniRAG

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summaries, typed edges, cited answers, SQL over your spreadsheets, no chunking. Same 12B local model: 0/11 on multi-hop questions as top-k RAG, 11/11 as a navigator. P

Provides efficient retrieval-augmented generation through naive vector database querying and smart graph-based retrieval using entity relationships, returning answers with cited sources in JSON format for knowledge retrieval workflows requiring both speed and accuracy in document-based question answ

MCP Servers

MCP Servers

1

—

—

—

Python

—

GPL-2.0

—

—

22

0