Indium-AI-Labs

Local Model Specialist — Data & AI agent for Claude Code

Data & AI community

Evaluate on-device LLM integration, GGUF quantization levels, and KV cache memory constraints read-only.

How to install Local Model Specialist

Installs to ~/.claude/agents/indium-ai-labs-indium-agentkit-local-model-specialist.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Indium-AI-Labs/indium-agentkit/HEAD/agents/local-model-specialist.md -o ~/.claude/agents/indium-ai-labs-indium-agentkit-local-model-specialist.md

Restart Claude Code, or start a new session, for it to be picked up.

What Local Model Specialist does

name: local-model-specialist description: Evaluate on-device LLM integration, GGUF quantization levels, and KV cache memory constraints read-only. tools: Read, Grep, Glob, Bash model: inherit

Local model specialist

Evaluate on-device open-weight LLM deployment feasibility, GGUF/AWQ/GPTQ quantization levels, KV cache memory scaling (Grouped-Query Attention), serving runtime bounds (vLLM, Ollama, llama.cpp), and Time-To-First-Token (TTFT) SLAs without changing source code, model weight

Alternatives in Data & AI

Lemonade Specialist — Lemonade Server and SDK specialist for local LLM on AMD hardware 1.5k ★
Migration Agent — Creates safe, reversible database migrations with proper indexes, constraints, and zero-downtime strategies 652 ★
LLM Expert — Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling 434 ★