Configure RuVLLM for local inference and fine-tuning.
When to use
When you need to configure local LLM inference, create MicroLoRA adapters for task-specific fine-tuning, or set up SONA for real-time adaptation.
Steps
Check status — call mcp__plugin_ruflo-core_ruflo__ruvllm_status to see current model and adapter state. If wasm.available is false, install the add-on first (npm i -g @ruvector/ruvllm-wasm, or without -g in a project) — the MicroLoRA and SONA tools cannot run without it
Generate config — call mcp__plugin_ruflo-core_ruflo__ruvllm_generate_config with model parameters
Create MicroLoRA — call mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_create with inputDim, outputDim, rank (1-4, default 2) and alpha
Adapt MicroLoRA — call mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adapt with loraId and a quality signal (0.0-1.0), optional learningRate and success. It takes a feedback score, not a training set
Create SONA — call mcp__plugin_ruflo-core_ruflo__ruvllm_sona_create with hiddenDim (default 64), learningRate and patternCapacity
Adapt SONA — call mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adapt with sonaId and a quality signal (0.0-1.0)
MicroLoRA vs SONA
Feature
MicroLoRA
SONA
What it is
Ultra-light LoRA adapter, rank 1-4
Instant adaptation loop (the tool describes <1ms cycles)
Input
quality feedback per call
quality feedback per call
Persistence
None: instances live in the MCP server's memory and are lost on restart
None: same
Neither tool fine-tunes a hosted model or writes adapter files; both adjust small in-process weights from quality scores. Keep the returned loraId / sonaId for later calls, and re-create them after a restart. For the repo's measured SONA latency see docs/reviews/intelligence-system-audit-2026-05-29.md.
1---2name: llm-config-23description: "Configure RuVLLM local inference helpers: generate a config, and create and adapt in-process MicroLoRA and SONA instances from quality signals. Use when you need local, air-gapped inference tooling, not for fine-tuning hosted models."4argument-hint: "[--model MODEL] [--adapter microlora|sona]"5allowed-tools: mcp__plugin_ruflo-core_ruflo__ruvllm_generate_config mcp__plugin_ruflo-core_ruflo__ruvllm_status mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_create mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adapt mcp__plugin_ruflo-core_ruflo__ruvllm_sona_create mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adapt Bash6metadata:7 source: https://skillmd.com/skills/ruvnet/llm-config-28---910# LLM Configuration1112Configure RuVLLM for local inference and fine-tuning.1314## When to use1516When you need to configure local LLM inference, create MicroLoRA adapters for task-specific fine-tuning, or set up SONA for real-time adaptation.1718## Steps19201. **Check status** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_status` to see current model and adapter state. If `wasm.available` is `false`, install the add-on first (`npm i -g @ruvector/ruvllm-wasm`, or without `-g` in a project) — the MicroLoRA and SONA tools cannot run without it212. **Generate config** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_generate_config` with model parameters223. **Create MicroLoRA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_create` with `inputDim`, `outputDim`, `rank` (1-4, default 2) and `alpha`234. **Adapt MicroLoRA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adapt` with `loraId` and a `quality` signal (0.0-1.0), optional `learningRate` and `success`. It takes a feedback score, not a training set245. **Create SONA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_sona_create` with `hiddenDim` (default 64), `learningRate` and `patternCapacity`256. **Adapt SONA** — call `mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adapt` with `sonaId` and a `quality` signal (0.0-1.0)2627## MicroLoRA vs SONA2829| Feature | MicroLoRA | SONA |30|---------|-----------|------|31| What it is | Ultra-light LoRA adapter, rank 1-4 | Instant adaptation loop (the tool describes <1ms cycles) |32| Input | `quality` feedback per call | `quality` feedback per call |33| Persistence | None: instances live in the MCP server's memory and are lost on restart | None: same |3435Neither tool fine-tunes a hosted model or writes adapter files; both adjust small in-process weights from quality scores. Keep the returned `loraId` / `sonaId` for later calls, and re-create them after a restart. For the repo's measured SONA latency see `docs/reviews/intelligence-system-audit-2026-05-29.md`.
Run npx get-skill add ruvnet/llm-config-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
LLM Configuration It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
ruvnet (@ruvnet) published this skill. Their other Agent Skills are listed on their SkillMD profile.