What TGM is

Temporal Graph Memory (TGM) turns your documents into a knowledge graph and answers questions with exact passages from them. There is no language model in the engine, so it cannot make things up.

How it works

1. You send documents through the API.
2. TGM splits them into passages and connects the passages into a graph, using embeddings alone.
3. You ask a question in plain language.
4. You get the exact passages back, each naming the file it came from. If the answer is not in your documents, you get not_covered: true instead of a guess.

What makes it different

Most retrieval products pass your documents through a language model, and language models can invent text. TGM serves bytes from your own files or refuses. An answer is always checkable: every passage names its source, and asking the same question again returns the same answer.

Every change to a graph is also a saved version. You can ask last month’s version a question and get last month’s exact answer, which makes answers auditable long after the documents change.