Skip to content
agentusehub

Configure a local AI lab and build a knowledge graph by chat

Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.

Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.

Reported experience

  1. What they did

    Per this overview, Ivan Fioravanti showed Hermes Agent setting up a local AI lab (liteLLM, Postgres, Prometheus, Grafana) through conversation. Separately, Alvaro Cintas had Hermes install Gbrain, an open-source project from Garry Tan, add it as an MCP server, and query it for entity-aware recall as a personal knowledge graph.

  2. How it went

    The source names both setups as working demos. It cites Gbrain's own benchmark of 31 points more precise than plain vector search. It gives no setup time, costs or failures for either one.

  3. Worth knowing

    The source only briefly describes these examples, so check the original posts by Fioravanti and Cintas for the actual steps. Hermes needs at least a 64K-token context.

Example prompts

Try with Hermes Agent
Set up a local AI stack on my machine with [liteLLM, Postgres, Prometheus, Grafana, or tools you choose], then install [Gbrain or another MCP knowledge-graph server] so I can build a personal knowledge graph from [my notes folder]. Explain each install step before you run it and ask me before deleting or overwriting anything. Finish by showing that each service is running and giving me a test query that works.
Software & DevOps

Port a Chrome extension to Safari

The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.

ChatGPT