Private preview for macOS

EU AI Act lineage. By August 2.

Article 10 requires documented data lineage for high-risk AI. Xorq makes every agent answer cited, versioned, and lineage-tracked — on Snowflake, Databricks, or your existing warehouse. Pair with Claude, Cursor, or any LLM.

Open source · github.com/xorq-labs/xorq

01 Interop

Agents that move with your data. Same expressions on your laptop and in your warehouse. Snowflake, BigQuery, Databricks, DuckDB.

02 Lineage

Cited by construction. Every answer carries its expression hash, the inputs it was derived from, and the chat that produced it.

03 Cache

Cached + hashed for speed. Same expression → same hash → instant. No re-execution, no re-billed tokens.

01 Local-first by design

On your laptop, with your keys.

A native Mac binary that uses your LLM key and your warehouse credentials. Bulk data stays in your warehouse — only the aggregates an expression needs cross into the local sandbox. No proxy, no token markup.

02 Cited by construction

Unbreakable lineage.

Every answer ties back to a cataloged expression. Auditable today; auditable in six months.

03 Bring your warehouse

No migration. No proxy.

Connects to Snowflake, BigQuery, Databricks, Postgres, DuckDB. The catalog sits alongside your warehouse, not in place of it — and one expression can compose data across multiple backends in a single pipeline.

04 An opinionated agent harness

A harness built for data work.

Claude Code and Cursor were built for code. Xorq routes every tool call through the catalog — cited, cached, reproducible. Opinionated by design, shaped by years of running data pipelines in serious orgs. The LLM is swappable; the harness is what we ship.

05 Replay any answer

Spans, cache hits, replayable.

Open any answer for the spans, hits, and durations behind it. Replay a single tool call. Diff against last week.

06 The proof, in benchmarks

Smaller model. Better answers.

DABStep — 450 questions over payment data. Same model, same prompt. Only the catalog changes. Haiku + catalog beats Sonnet baseline in half the turns.

Read the full story →

07 Things people ask first

What is Xorq Desktop?

A native Mac binary. Point it at your data, pick a workflow, and an agent works against a shared catalog of cited expressions.

When can I use it?

Private preview. Waitlist for the desktop; the library (uv add xorq) ships today.

Do I need to migrate my data?

No. Connects to Snowflake, Databricks, DuckDB, S3, Postgres — whatever you already run.

What is the “catalog”?

An immutable store of executable expressions. Each entry: expression + metadata + cached result, addressed by hash. Agents compose new entries on top of old ones.

How is this different from a notebook + an LLM?

Notebooks accumulate output. Xorq accumulates work. Last week’s expression is still here, still addressable; the next agent picks up where the last one left off.

Two people, same question — conflicts?

Same expression → same hash → automatic dedup. Identity is content, not file path.

Linux / Windows?

Desktop is Mac-first. The library and Textual TUI run everywhere Python does.

08 Two paths to the same harness

Pick how you adopt.

Run our integrated harness, or layer xorq’s primitives into the harness you already use. Same catalog. Same open-source library.

01 Our harness private preview

Xorq Desktop

The integrated harness. Open the app, point it at your warehouse, ask. Agent, catalog, and lineage in one native binary. No terminal.

$ open Xorq.app

02 BYO harness open source

Claude Code × xorq

Already in Claude Code? Layer the same catalog, lineage, and guardrails in as a plugin. No app, no migration.

> /plugin marketplace add xorq-labs/claude-plugins
> /plugin install xorq@xorq-plugins

status

Agents come and go. What compounds is the catalog — composable memories the next agent builds on.

Not the agents. The work.