Features
l0l1 does four things well: it validates SQL against your real schema, protects PII at the boundary, learns your team's approved query shapes, and integrates with the tools you already use. Everything below is in the open-source project — no hosted service required.
Validate
Treat LLM-generated SQL as a draft and check it against your real schema before it runs.
Schema-aware validation
Every query is checked against the live schema of the connected database — real columns, real relationships. Catches SQL that is locally plausible but silently wrong against your actual tables.
AI reviewer, not author
l0l1 treats LLM output as a draft to be reviewed. Validation runs through OpenAI or Anthropic (pluggable providers) to reason about intent and correctness before a query ships.
Any SQL origin
It does not matter whether a human, ChatGPT in a browser tab, or an internal tool produced the SQL. l0l1 sits at the boundary and validates whatever is about to run.
Protect
Detect and anonymize PII at the prompt and query boundary, before data leaves the room.
PII detection on prompts + queries
Microsoft Presidio plus additional regex rules scan for SSNs, emails, phone numbers, and credit card numbers in both prompts and query text before anything leaves the local process.
Anonymize before forwarding
Detected PII literals are anonymized before queries are stored or forwarded to an external model provider — reducing what raw data crosses the tool-to-provider boundary.
Boundary-aware design
l0l1 reasons about four boundaries — user-to-tool, tool-to-model-provider, tool-to-warehouse, and warehouse-to-output — and applies protection at each one.
Learn
Grow a per-workspace library of approved query shapes and surface them as completions.
Per-workspace pattern learning
Successful queries are sanitized of literals and stored as shape patterns per workspace, then surfaced as completions for the next person — a learning loop grounded in your own approved SQL.
Completions from approved shapes
Instead of inventing SQL, l0l1 suggests query shapes your team has already run and verified. The library grows with real usage, not synthetic examples.
Integrate
Meet SQL where it is written: CLI, REST API, Jupyter, and the editor.
CLI + REST API
A Typer-based CLI for local checks and a FastAPI REST server for pipeline integration. Validate, scan for PII, and request completions from either surface.
Jupyter magic
A notebook magic brings validation and PII scanning inline, so analysts get feedback in the same cell where they draft SQL.
VS Code + LSP
A VS Code extension built on an LSP server surfaces validation and completions directly in the editor as you write SQL.
Four database connectors
Connects to PostgreSQL, MySQL, SQLite, and DuckDB. Schema introspection is cached so validation stays fast against large warehouses.
Honest scope
l0l1 is not a text-to-SQL system and makes no compliance claims by transitivity. There is no differential privacy or homomorphic encryption — result rows are exact. If you configure OpenAI or Anthropic, query text and schema context are sent to that provider. PII detection is best-effort. See the FAQ for the full picture.