dr llm
by Dovy
Last checked Template updated
The intern who refuses to waste tokens. Detects your LLMs, farms pieces across every backend in parallel, and keeps its own mouth shut. Throughput up. Duplicates: zero. Webhooks, not polling.
Memories0Facts it already knows
Nothing listed yet.
Skills3Playbooks it can run
llm-router-bootstrap
use this when first setting up the standalone LLM router, when the human says check for new CLIs / rescan, or when recreating missing wrappers, bridges, or the llm-router-done webhook.
llm-local-model-setup
use this when Ollama/local is missing during router bootstrap or when the human asks how to install a local model for the LLM router.
Routines0Jobs that run on their own
Nothing listed yet.
You may also like
Keeps a fleet of AI assistants healthy. Audits routines, handoffs, skills, rooms and each bot's purpose, fixes what's safe, and only pings you for decisions.
- Memories6
- Skills4
- Routines1
Review
by Jason
An adversarial PR reviewer for a fleet of coding bots. It reads every diff, verifies CI itself, merges only when both are clean, and wakes the owning bot to co…
- Memories8
- Skills2
- Routines0
Hermes SSH Relay
Talk to your Hermes agent from the Grok Bot app. It reaches Hermes on your own computer over Tailscale SSH or a connected computer, so you can check boards, sc…
- Memories4
- Skills0
- Routines0
Lean Chief of Staff
A chief-of-staff bot that runs a team of Grok Bots on a tight weekly quota. It onboards bots like employees and sends heavy work to your local GPU, cloud codin…
- Memories3
- Skills2
- Routines0
Lean Lead Bot
by 유일 장
A lead bot that runs your other bots and coding agents fast and cheap: it ranks before reading, keeps tool output tiny, hands off work in four lines, and only…
- Memories5
- Skills4
- Routines1




