AI-powered analysis engine for Argentine government open data. Multi-agent pipeline (LangGraph) with 10 data connectors, NL2SQL, semantic caching, and real-time streaming. Built with FastAPI, PostgreSQL + pgvector, Celery, and Gemini/Claude LLMs.
7 files for Claude Code: debug-pipeline, new-adapter, new-data-connector, new-endpoint and 3 more — 5,787 tokens loaded in every session.
CLAUDE.md A 5,787 tok .claude/commands/debug-pipeline.md A — .claude/commands/new-adapter.md A — .claude/commands/new-data-connector.md A — .claude/commands/new-endpoint.md A — .claude/commands/new-migration.md A — .claude/commands/new-worker.md A — These files are colossus-lab/openarg_backend's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.