Google's AI research engine: upload PDFs, documents, slides, or web pages into a notebook; Gemini embeds and retrieves the relevant passages and answers with clickable citations back to the exact source, plus generated audio overviews. Near-zero setup, and scoped strictly to the sources you uploaded.
Grounded, cited answers over a bounded set of your own sources — our research describes it as answering "with clickable citations" and refusing "if evidence isn't present." This is arguably the best citation experience surveyed anywhere on this matrix, and it's a shipped, working feature rather than a design intent — free to use, with a paid Plus tier for higher limits, and effectively zero setup beyond uploading sources.
Both are explicitly grounded-retrieval systems built to refuse answering from thin air — Mimir's provenance chain (GET /provenance/:chunk_id) and NotebookLM's clickable citations are solving the same trust problem from different architectures.
NotebookLM is scoped to whatever you deliberately uploaded into one notebook; Mimir is designed as a standing, continuously-capturing memory across everything — Slack, Drive, Asana, and fast-lane thoughts — rather than a per-project research tool. Mimir also adds the compulsory governance layer and an agent-facing audited API; NotebookLM is a human-facing product with no public agent/API surface.
Actual semantic retrieval, right now. NotebookLM's embeddings are live and its citations are a shipped, polished feature. Mimir's pipeline, schema, HNSW vector index and search function are all built and working — the embedding column just sits at 0% coverage today because the provider decision (hosted API vs. local) is still open, not because anything is broken, so retrieval is lexical-only until that closes. On the one row both systems compete on directly, grounded retrieval quality, NotebookLM is ahead today.
Grounded in our research on the zero-structure/RAG school.