LLMSkillHub
mirroredCopied from ShaftHQ/SHAFT_ENGINE under MIT. ShaftHQ has not claimed this page, and is not affiliated with LLM SkillHub.

shafthq / local-runtimes

Use when choosing an optional local inference runtime for a narrow mechanical or offline job. One table routes to OmniRoute, FreeToken, Colibri, a loopback server, or the hardware probe.

0
SKILL.md
1.7 KB

Local runtimes

Cloud implementers write code directly. A local runtime is optional
and only pays for narrow mechanical or offline jobs; never let it review its
own diff. Pick one row, then open only that route.

NeedRouteOpen
Which model size fits this machinehardware probe[local-coding-delegate](references/local-coding-delegate.md)
Already READY loopback server (Ollama, LM Studio, llamacpp)loopback[local-openai-compat](references/local-openai-compat.md)
Standalone FreeToken processFreeToken[freetoken](references/freetoken.md)
Frontier MoE through disk/RAM/VRAM tiersColibri[colibri](references/colibri.md)
OmniRoute runner with delegate continuityOmniRoute[omniroute](references/omniroute.md)
Local agents (OpenCode / OSS agency)agency[local-agency](../local-agency/SKILL.md)

FreeToken and Colibri share the [loopback runtime contract](references/loopback-runtime-contract.md).

Rules:

  • A runtime is used only when its READY probe passes; otherwise stay on the
    cloud implementer and record local: skipped(<reason>) once.

  • One-shot jobs only: one short spec in, one digest out. No parent relay.

  • Avoided-spend metering and USD/EGP lines are required only when a local
    inference channel was actually used
    ([process owner](../../references/process-owner-scrum-master.md)).

  • Descriptions, paths and host exposure live in the
    [catalog](../../references/catalog.md).