Six-figure document review, at the cost of the electricity.
An open-source eDiscovery responsiveness review engine that runs entirely on hardware you control. Bring your own GPU. Keep your own documents. End with a certificate a frontier model cannot supply.
Open code, open specifications, version-pinned by design.
Court-defensible technology-assisted review does not require a proprietary black box.
It requires four controls: per-request rubrics locked by cryptographic hash before classification begins; a calibrated classification cascade optimized under explicit recall constraints; a deterministic privilege screen that routes every flagged document to attorney-only review; and a formal validation stopping rule that issues a Defensibility Certificate only when per-request recall bounds, elusion bounds and active-learning convergence are all satisfied.
The claim is procedural: defensibility turns on a measurable, documented, counsel-supervised process that an opposing party, special master or court-appointed expert can reproduce, not on trust in any particular model.
Four controls, one certificate.
Bring your own GPU. Keep your own documents.
The pipeline makes zero calls to any AI vendor’s API. There is nothing for anyone to subpoena from us, because we never have your documents. That is not a privacy policy; it is an architecture you can read in the source.
Determinations per request, with receipts
Every document is scored against each request for production individually, with the criteria matched, the exclusions triggered, and citation spans quoting the exact text the call relied on.
Defensible by construction
Privilege screening runs first and deterministically. Confidence scores are calibrated on your own matter with hard gates that lock auto-accept when calibration degrades. The review ends in a Defensibility Certificate: per-request recall bounds, elusion measurement, and an audit chain hash-pinned to the exact criteria and thresholds used.
Priced like electricity, not like a platform
The GPU meter runs while the job runs and then stops. About $70 of compute for 100,000 documents, whether your case settles in four months or goes to trial in four years.
Wired into Discovery Framework
Sign the certificate and the responsive set, the per-request determinations and the citations flow straight into Discovery Framework: answers grounded in the responsive documents, the gaps in the other side’s production, the meet and confer letter, the Motion to Compel.
Discovery Framework →Measured, not promised
The system does not ask whether the point estimate looks good. It asks whether the lower bound clears the floor. Matter-level claims issue only through signed validation certificates; the worked example in the paper is proof of pipeline arithmetic, not a production claim.
A court-defensible artifact a frontier model cannot supply.
The Defensibility Certificate is the artifact you hand to a special master or a court.
Issued only when every gate is satisfied: a per-request recall lower bound above the floor, an elusion upper bound below the ceiling, and active-learning convergence. Hash-pinned to the rubric, the cascade, the calibration and the audit log. Signed by counsel. There is no override for a hash failure.
The paper is published. The code follows it.
Documented first, released second.
The methodology, the four controls and the certificate are set out in the paper on SSRN, which is the public artifact today. The source, the specifications, the quickstart and the release tag publish together at the first public release, under Apache 2.0. We do not put an install button on a page before there is something behind it.
Read the paper →No gate, no freemium nag, no feature-crippling.
When it is released, it is released whole: self-hosted, no vendor API calls, no metered anything. The move from isResponsive() to LitigationOS is a sequence a firm chooses, never a paywall it runs into.
Until then, the engine is shown in a demo, on documents we bring, so you can watch the privilege screen, the per-request determinations and the certificate arithmetic in one sitting.
Read the paper. Check the arithmetic.
The methodology is written down, the worked example shows the pipeline arithmetic, and the Four Laws we build by are in the same paper. Read it before you believe a number on this page.