-49
Hivekeep - self-host a team of AI agents in one container, with a real UI (MIT) (github.com)
submitted 4 months ago by to c/selfhosted@lemmy.world
10 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 4 months ago* (last edited 4 months ago) (4 children)

This looks interesting, especially the persistent memory. I want to try it out but it seems likely to me that multiple simultaneous agents would require significant hardware. Even if they were serially activated, reloading contexts with each switch would take time. I have a pretty beefy GPU and experience significant (almost ridiculous) slowdown when opencode runs 2 subagents simultaneously.

But perhaps the memory storage/lookup keeps contexts very small?

Anyway, I can't find any mention in the repo or docs what the suggested minimum hardware is.

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] [S] 0 points 4 months ago (2 children)

    Good question, and you're right that it's missing from the docs (just added a Hardware requirements section to the README to fix that).

    The key thing: Hivekeep doesn't run the models itself. It calls your provider (Anthropic/OpenAI/etc.) or a local OpenAI-compatible endpoint, so the heavy compute lives there, not in the app. The platform itself is a single Bun process over SQLite, no GPU, no extra services. It runs in well under 1 GB of RAM on a small home server.

    On the multi-agent worry: agents are activated serially per message, not all firing at once, and the persistent memory is exactly what keeps each context small (hybrid vector + keyword recall, re-ranked, instead of replaying the whole history). So adding agents mostly means more calls routed to your provider, not multiplied local load.

    The opencode slowdown you saw is on the inference side: if you point Hivekeep at local models (llama.cpp / LM Studio / Ollama / vLLM), the hardware question moves to your inference server, same as any other client. If you use a hosted provider, your machine barely feels it.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 4 months ago

    Yeah, my thinking was definitely biased to my environment. I selfhost llama.cpp so even if Hivekeep doesn't require significant resources, whatever LLMs it runs will use my hardware.

    agents are activated serially per message, not all firing at once, and the persistent memory is exactly what keeps each context small

    It sounds like I need to try it!

  • permalink
  • fedilink
  • source
  • parent