A Rust and SQLite rebuild of graphify for code graphs on very large repos
Emerged finds new products worth a look, daily — what’s new today
GraphRAG on plain Postgres where newer documents retire facts from older ones
If your retrieval keeps citing last year's org chart, this keeps the graph, vectors and time-bounded facts in the Postgres you already run.
Post-graph-RAG is a Python library that builds a knowledge graph inside PostgreSQL next to pgvector embeddings, so there is no separate graph or vector store. An LLM extracts entities and relations; when a later document contradicts an earlier one, the old relation is closed with a validity period. Retrieval fuses graph traversal, relation embeddings and BM25. It ships on PyPI under Apache-2.0 with tests, docs and an arXiv write-up by Chandan Rajah; its benchmark wins are self-run.
A Rust and SQLite rebuild of graphify for code graphs on very large repos
A single-file graph store you can query as it stood on any past date
Draw who knows whom, then find the shortest chain between any two people
Publish interactive charts from your data or from OECD, WHO and World Bank sets
Open-source text-to-SQL you can tune and measure on your own database
A free desktop SQL and Redis client with no cap on open tabs