RAG Specialist — Development agent for Claude Code
GAIA RAG and agentic-retrieval specialist.
How to install RAG Specialist
Installs to ~/.claude/agents/amd-gaia-rag-specialist.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/amd/gaia/HEAD/.claude/agents/rag-specialist.md -o ~/.claude/agents/amd-gaia-rag-specialist.md Restart Claude Code, or start a new session, for it to be picked up.
What RAG Specialist does
name: rag-specialist description: GAIA RAG and agentic-retrieval specialist. Use PROACTIVELY for RAG pipeline work, document indexing, embeddings, semantic chunking, or integrating RAG into agents via the `rag` tool mixin. tools: Read, Write, Edit, Bash, Grep, Glob model: opus
You own GAIA's retrieval-augmented generation stack: the `RAGSDK`, the `RAGToolsMixin` (registered as `rag` in `KNOWN_TOOLS`), embeddings, and chunking strategies.
Output style
Follow [`CLAUDE.md`](../../CLAU
Alternatives in Development
- Context Restore — Expert Context Restoration Specialist focused on intelligent, semantic-aware context retrieval and r... - wsho 31.9k ★
- Claude Context Local — Code search MCP for Claude Code 201 ★
- Code Refactor Agent — Duplicate code detection and refactoring specialist 149 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Vector Store Indexer
MUST BE USED PROACTIVELY for indexing and semantic search across the file system. This agent creates vector em
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Semantic Search
Reference semantic-search backends when changing indexing, retrieval, persistence, or concurrency behavior.
GitHub Actions Specialist
GitHub Actions / CI specialist for GAIA. Use PROACTIVELY for creating or modifying workflows under .github/wor
Backend RAG Specialist
Use for isolated server-side API, retrieval, and knowledge-base work in server/, especially route behavior, se
Local Brain Search
Local vector search and connection discovery for the Brain. Use for semantic search, finding connections betwe
Related Skills
Ragent
Agentic RAG chatbot that answers questions from uploaded PDFs using semantic search (FAISS + embeddings), with
Obsidian Vault RAG Assistant
Obsidian Vault RAG Knowledge Assistant: local MiniLM embeddings + numpy retrieval, measured eval harness (reca
Docwise Agentic
Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct