projectchrono

RAG Search — AI skill for Claude Code

AI community

Run a local Chrono/PyChrono retrieval search for: $ARGUMENTS.

How to install RAG Search

Installs to ~/.claude/commands/projectchrono-chrono-rag-rag-search.md

Terminal
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/projectchrono/chrono-rag/HEAD/.claude/commands/rag-search.md -o ~/.claude/commands/projectchrono-chrono-rag-rag-search.md

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

What RAG Search does

Run a local Chrono/PyChrono retrieval search for: $ARGUMENTS

Run this from the repository root (uses the local index; no API key needed):

conda run -n chrono-rag chrono-rag search "$ARGUMENTS"

Then report the returned chunks (file paths, line numbers, and snippets) to the user. Results target the Chrono checkout named in the printed scope line (by default a dated snapshot of Chrono main); report that scope to the user. If the search reports low confidence / insufficient evidence,

Alternatives in AI

  • RAG Skill — A Skill dedicated to local knowledge base retrieval 712 ★
  • Kindly Web Search MCP Server — Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C 377 ★
  • Ataru — High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus 351 ★

Full documentation available on GitHub

View Source Repository