Verifiable AI for enterprise data teams

The semantic catalog that makes AI answers verifiable — on Snowflake, Databricks, and 20+ backends.
Private preview for macOS

Your AI guesses at numbers. Xorq makes it prove them.

Xorq grounds every answer in a semantic catalog of cited expressions — on the warehouse you already trust — so a hallucinated number gets caught and corrected before it reaches the boardroom.

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

01 Verified
A verifier checks every number. Lineage, data-quality, and faithfulness subagents run alongside the work, so a hallucinated total gets flagged and corrected before anyone acts on it.
02 Governed
Built only on blessed sources. Agents compose new expressions only on sources a human signed off on, so ground truth stays under change control with an audit trail by construction.
03 Efficient
Lower AI spend by construction. Reruns hit cache — Snowflake doesn’t bill the same answer twice — and a smaller model does the work: 60% fewer tokens on DABStep.
01 Local-first by design

No new vendor in your data path.

A native Mac app on your own LLM subscription and warehouse credentials — no vendor cloud to clear through security review. Git-native: catalogs are repos, promotion to main is the governance event. Bulk data stays in the warehouse; only aggregates cross into the local sandbox.

02 Cited by construction

Unbreakable lineage.

Agents compose only on sources a human blessed. Every answer ties back to a cataloged expression — source, cache, schema — so when an auditor asks where a number came from, the answer is one click, reproducible six months later.

03 An opinionated agent harness

The platform team you don’t have to hire.

Governed AI usually means engineers standing up MCP servers, permission services, and agent rigs. With Xorq that layer comes with the install: every tool call routes through the semantic catalog and clears verification gates before an answer reaches your team. The LLM is swappable; the harness is what we ship.

04 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.

05 The proof, in benchmarks

Better answers at lower model spend.

DABStep — 450 questions over payment data. Same model, same prompt, only the catalog changes — and Haiku + catalog beats Sonnet baseline on 60% fewer tokens and half the turns. Accuracy and cost savings come from the same place: the catalog.

Read the full story →
06 The open-source core · Apache-2.0

An executable memory layer for data work.

Markdown memory burns tokens: the agent reads its notes, writes a one-off script, runs it, and throws it away. Xorq’s memory is executable — durable, content-addressed expressions that run as-is, so the next agent hits cache instead of re-deriving. That’s where the tokens and turns go.

Star 510

Declarative Ibis expressions that run the same on your laptop or your warehouse. The semantic catalog that powers Xorq Desktop.

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.
Do I need to set up an MCP server?
No. The catalog, gates, caching, and warehouse connections come with the install — nothing to build or babysit.
How does this get through security review?
It runs on the analyst’s Mac with your existing warehouse credentials and LLM subscription — no vendor cloud in the data path, so no new data processor to assess.
What is the “semantic catalog”?
An immutable store of executable semantics: expression + metadata + cached result, addressed by hash. Metric definitions live here as runnable code; 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.
# the catalog is open source · the coworker is in private preview
JOIN THE WAITLIST ESC

Drop your email — we’ll add you to the Mac preview rollout and send a build when one is ready for your setup.

You can unsubscribe anytime. We don’t share emails.

KEYBOARD SHORTCUTS ESC
HHOME
GGITHUB
DDOCS
RJOIN WAITLIST
JSCROLL DOWN
KSCROLL UP
⌘KTOGGLE THIS GUIDE