RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an
https://arxiv.org/abs/2607.11683v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm, ai
Overlap with sectors you care about
Geography
Unknown
Location unknown — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
M
Mikhail Komarov
1.0
low confidence
I
Ivan Bondarenko
1.0
low confidence
S
Stanislav Shtuka
1.0
low confidence
O
Oleg Sedukhin
1.0
low confidence
R
Roman Shuvalov
1.0
low confidence
Y
Yana Dementyeva
1.0
low confidence
M
Matvey Solovyov
1.0
low confidence
N
Nikolay O. Nikitin
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Ardis AI
· Inactive
Transform your text data into a searchable knowledge graph
founders not scraped yet
HelixDB
· Active
The fastest & most scalable graph-vector database on the market
founders not scraped yet