llm-config
Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation
Best for local inference setupWorks with GitHubLow risk
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Check current model/adapter status
- ·Generate config with model parameters
- ·Create MicroLoRA adapters for task tuning
- ·Adapt MicroLoRA with training data
- ·Create SONA for real-time neural adaptation
- ·Adapt SONA with feedback signals
Use Cases
- →Configure local LLM inference with specific model
- →Fine-tune a model for a specialized task using MicroLoRA
- →Set up real-time adaptation with SONA for dynamic environments
Best for
- ✓local inference setup
- ✓task-specific fine-tuning
Not ideal for
- !cloud-based LLM deployments
- !quick one-off generation without tuning
name
llm-config
description
Configure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptation
argument-hint:[--model MODEL] [--adapter microlora|sona]
allowed-tools:mcp__claude-flow__ruvllm_generate_config mcp__claude-flow__ruvllm_status mcp__claude-flow__ruvllm_microlora_create mcp__claude-flow__ruvllm_microlora_adapt mcp__claude-flow__ruvllm_sona_create mcp__claude-flow__ruvllm_sona_adapt Bash
LLM Configuration
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__claude-flow__ruvllm_statusto see current model and adapter state - Generate config — call
mcp__claude-flow__ruvllm_generate_configwith model parameters - Create MicroLoRA — call
mcp__claude-flow__ruvllm_microlora_createfor task-specific adapters - Adapt MicroLoRA — call
mcp__claude-flow__ruvllm_microlora_adaptwith training data - Create SONA — call
mcp__claude-flow__ruvllm_sona_createfor real-time neural adaptation - Adapt SONA — call
mcp__claude-flow__ruvllm_sona_adaptwith feedback signals
MicroLoRA vs SONA
| Feature | MicroLoRA | SONA |
|---|---|---|
| Speed | Minutes to train | <0.05ms adaptation |
| Scope | Task-specific fine-tuning | Real-time micro-adjustments |
| Persistence | Saved as adapter weights | Session-scoped |
| Use case | Specialized domain tasks | Continuous feedback loops |
$install
1-click copynpx skills add ruvnet/ruflo --skill llm-configSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.