LLM Architect — Data & AI agent for Claude Code
LLM and agent cognition expert.
This agent role-plays Andrej Karpathy. It is third-party content from
nicepkg/agent-world, not written, endorsed by or affiliated with Andrej Karpathy.
How to install LLM Architect
Installs to ~/.claude/agents/nicepkg-agent-world-llm-architect.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nicepkg/agent-world/HEAD/.claude/agents/llm-architect.md -o ~/.claude/agents/nicepkg-agent-world-llm-architect.md Restart Claude Code, or start a new session, for it to be picked up.
What LLM Architect does
name: llm-architect description: "LLM and agent cognition expert. When to use: brain plugin design, prompt engineering, agent reasoning, LLM provider integration, token optimization, agent personality systems." model: inherit
LLM Architect — Andrej Karpathy
Role
Chief LLM architect. Designs how agents think, reason, and communicate using language models. Owns the brain plugin, prompt templates, and LLM provider abstraction.
Persona
You are Andrej Karpathy, former Director of A
Alternatives in Data & AI
- Multi Agent Systems Architect Agent — Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover 669 ★
- LLM Expert — Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling 434 ★
- General Backend Developer — Use this agent proactively when you need to design, implement, or optimize backend API systems, including REST 248 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,
AI Provider Expert
Primary reviewer for AI provider integrations, model routing, embeddings, prompt systems, streaming, token eff
AI Data Specialist
Deep AI/data engineer — LLM integration and agent systems, RAG, evals, data pipelines, and ML productionizatio
Cortex
ML/AI engineer — LLM integration, prompt engineering, RAG, evals, and AI feature design for production
LLM Integrator
LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements
Budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits
Related Skills
Twin Sparrow Architect Review
Composite architecture review skill combining Oppus reasoning discipline with expert engineering review for sy
Claudemd Architect
Generate production-grade CLAUDE.md files that steer AI coding agents. Incorporates LLM reasoning failure miti
Systems Thinking
A cognitive base that shifts AI agent reasoning from linear cause-effect chains to feedback-driven structural