memFrame

memFrame brings a pandas-like DataFrame API to DuckDB, PostgreSQL, and ClickHouse — async-first, with an optional AI agent for natural-language data work.

What It Provides

• Database-backed DataFrame API across DuckDB, PostgreSQL, and ClickHouse.
• Each pandas-style call is compiled to backend-native SQL and executed on the engine — your data never leaves the database.
• Async-first surface with sync equivalents for every operation.
• Upload from CSV, Parquet, or pandas DataFrame.
• Inspection, selection, cleaning, statistics, arithmetic, Plotly charts.
• Two-level cache: lineage audit + replayable result tables.
• Optional AI agent layer (memframe_ai) for natural-language data work.

Start Here

1. Follow Getting Started to connect and upload data.
2. Try the AI Agent for natural-language data work.
3. Read Upload Manager for ingestion behavior.
4. Read Dataset Operations to manage uploaded datasets.