Skip to content

aitherium/awskills

v1.0.0MIT

Portable agent skills for operating AI agents and the Aither/awdk toolchain. Instructions only: every skill is a SKILL.md that tells the agent a procedure. Some skills tell the agent to run local CLIs (adk, awnode) and fetch from github.com. Nothing is sent to Aitherium unless the user runs those tools against Aitherium's hosted services.

split-inference

Shard ONE model across MULTIPLE machines' GPUs with llama.cpp RPC — build with -DGGML_RPC=ON, start rpc-server on the backend hosts, launch the main server with --rpc, and PROVE the split is real instead of a silent local-only fallback. The reference topology is Bonsai-27B across the local 5090 and the DGX Spark over the ~1ms LAN.

Read SKILL.md at the source

Pinned to revision 685376e99ae5, so it is the text this page describes rather than whatever the author pushed since.

Pre-approved tools experimental

Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.

  • split_detect_topology
  • split_resolve_recipe
  • split_plan_deployment
  • split_apply
  • split_verify
  • Read
  • Bash

Files

Every link opens the file at its source, pinned to the revision this page describes.