Where do you store the Knowledge Graph? Are you supporting any Graph Database like FalkorDB?

I pre-configured it to use https://github.com/modelcontextprotocol/servers/tree/main/sr... which stores it in a JSON file, memory.json. However, user can freely configure it to use FalkorDB using https://github.com/FalkorDB/FalkorDB-MCPServer. Feel free to submit issue on github so I can support you better https://github.com/jolks/goto-assistant/issues/new

Did you consider using a Graph Database? e.g. FalkorDB? If you want to keep it lite we released a lite version that can run embedded in your nodejs.

I did consider, and ultimately decided I didn't want the overhead. Would love to talk with you about the lite version though.

That’s exactly why we released FalkorDBLite,an embedded graph engine designed for local, edge, and GenAI use cases (GraphRAG, agentic memory, semantic layers, code graphs, etc.).

https://www.falkordb.com/blog/falkordblite-embedded-python-g...

Nice! Do you plan to add support for other Graph Database (e.g. FalkorDB)?

Hi gkorland, you can already export to TTL that's easily ingestible in any Graph DB. We plan to expand the integrations soon as we get user feedback and requests for those

We're building an open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Allowing you to ask your database questions in plain English, QueryWeaver handles the "weaving".

https://github.com/FalkorDB/QueryWeaver/

can you share a link?

The fact that GQL is now supported by some of the relational Database, doesn't mean they'll become an alternative to native Graph Databases.

Yeah I guess it’s like saying that relational DBs supporting native JSON type meant the end of NoSQL DBs.

>relational DBs supporting native JSON type meant the end of NoSQL DBs

This holds true for 95% of cases of well-made software.

It pretty much did except for very specific use cases

You should check FalkorDB https://github.com/falkordb/falkordb

Not embedded last I checked. Unless that changed.

Did you try to run redis-benchmark? (Compared to Redis)

We built QueryWeaver exactly to solve those pain points—SQL generation that actually understands your business context and keeps the conversation alive across follow-ups. The graph layer is fully extensible, so you can define things like what an “active user” means for your org. Would love to hear your feedback if you give it a try!