What the community has built

A skill for the document-production phase of international arbitration within LegalQuant's LQAI. It builds and maintains the Redfern Schedule, the request-to-produce table at the heart of disclosure in arbitration, working from one shared artefact for all three roles: the requesting party drafting requests, the producing party stating objections, and the tribunal preparing to rule. It runs each request through the IBA Rules on the Taking of Evidence (2020) Article 3.3 admissibility checklist, maps objections to the Article 9.2 grounds, and raises a content-based political-sensitivity prompt for State and state-owned parties. Every citation is verified against its official source, and it produces a private flags memo telling you where your own requests or objections are weak before you serve them. It enforces form. The legal calls stay with you.

Alexios vdSKAssociate General Counsel

Witness Interivew Simulator is a full-system investigative interview simulator that allows lawyers and compliance professionals to practice conducting realistic regulatory interviews. It models witness behavior, interview structure, evidentiary confrontation, and downstream risk escalation to train investigative judgment in a safe, repeatable environment.

Veronica LopezInvestigations Attorney building with AI

A production B2C AI service [https://neshemyaka.ru] that predicts litigation and appellate risk for individual users and small businesses. It ingests raw case text, classifies case types, and returns a 0–100 risk score with a confidence score, along with structured risk factors and practical recommendations. Built on a Go backend with PostgreSQL and a multi-model LLM layer with fallbacks, the system is optimized for low COGS, robust JSON error handling, and fast UX (magic-link auth, HTMX frontend), making advanced legal risk analytics accessible without any enterprise integration.

Nikita PolyakovLegalTech Architect (ex-Litigator)

An experimental B2B predictive justice system currently in the R&D phase. Designed to eliminate uncertainty in commercial arbitration, Lexometrica functions as high-load legal infrastructure. The core architecture (Go/Python/PostgreSQL) utilizes a multi-LLM consensus pipeline to parse complex judicial patterns, evaluate litigation risk at scale, and build dynamic AI profiles of individual judges based on their past decisions and behavioral tendencies. The goal is to shift legal strategy from subjective human intuition to a statistically calibrated, API-first risk assessment model.

Nikita PolyakovLegalTech Architect (ex-Litigator)

A spatial research tool for Title 11 of the U.S. Code. Pull sections, defined terms, and cross-references onto a canvas; arrange them, follow the trail, save your work.

Rebecca FordonAssistant Director of Innovation, Research & Instruction

Ask natural language questions about any federal bankruptcy case — powered by documents freely available through the RECAP Archive and CourtListener API. Try the demo, install to add your own cases.

Rebecca FordonAssistant Director of Innovation, Research & Instruction

Verify legal citations against CourtListener. Catches hallucinated case citations from AI tools by checking whether a citation actually exists and belongs to the case it claims to.

Rebecca FordonAssistant Director of Innovation, Research & Instruction

Dashboard for tracking federal and state court local rules, standing orders, and judge-specific procedures. Features an AI-powered research agent for discovering court resources and automated URL tracking.

Alyssa SonesKnowledge & Innovation Attorney

Churci audits citations in your briefs and memos. But that is not the whole story. So what is Churci? - Paste your doc or upload a PDF/DOCX and it extracts every citation automatically. - It significantly lowers your AI cost by verifying through CourtListener first and only using AI when needed. - Verifies case law against CourtListener with deduping. - Flags outcomes clearly: Verified, Ambiguous, Needs Review, Hallucinated, or Misrepresented. - Shows legal context around each cite: the paragraph and the proposition being supported. - If a citation is fake/uncertain/mis-cited, it suggests plausible real replacements structured by binding authority, persuasive authority, and secondary sources grounded so you’re not swapping one hallucination for another. And given the power of Gemini 3, you can check your citations and get suggested real cases for a couple cents. All you need is your own Gemini API key and CourtListener API key which are both linked right in the configuration screen.

M. Onur KafkasGovernment Lawyer

Origynl is an early-stage prototype exploring document authenticity for the AI era. It combines multi-factor AI detection with blockchain certification to prove that a file — contract, photo, record — existed at a specific moment in time, isn’t AI-generated, and hasn’t been altered since. Still rough around the edges, but the core idea is simple: a tamper-proof notary for a world where anyone can fake anything.

Zachary BrennerFounder & JD/MBA Candidate

Mobile-friendly version of the Hong Kong Court Diary, updated daily with verifiable sources; allows filtering by judge and easy sharing with clients.

Rocky LiBuilder

A "selection, not generation" demo for drafting California discovery-response objections — with a chain inspector that shows every move.

Sean GalvinLitigation Defense Attorney & Legal Engineer

Proof-of-concept for deterministic, automated citation verification (does not use LLMs). The idea is to use something like this as an automated check before filing anything with a court, or to implement it *in* courts to alert court staff or judges to possible citation issues.

Ansel HalliburtonSenior Lead Counsel, Global Trademark Portfolio

Singapore court citation checker -- detect hallucinated cases in AI-generated legal submissions. Verifies citations against eLitigation (Singapore's case law database), detecting hallucinated authorities, mismatched case names, fabricated paragraph references, and distorted quotations.

Yu Chou TeoGovernment Lawyer

Legal verification tool to combat AI hallucinations.

Patrick MunroSenior Legal Counsel | Of Counsel

An open-access compendium containing over 1,000 arbitration-related judgments rendered by Hong Kong courts, built with Claude Code and Gemini 3.5

Troy Zhaoyi SongDisputes & Tech Lawyer

A multi-stage pipeline that screens major stock price drops nightly, runs plaintiff-style event-study damages estimates, then uses frontier LLMs to assess loss causation, falsity of prior disclosures, and insider-trading scienter signals. Automates the full case-evaluation workflow that securities fraud plaintiff firms currently do manually with economists and senior associates.

John HughesSpecial Counsel, Litigation

A pro bono platform for immigration habeas attorneys. Helps lawyers draft and file emergency habeas petitions fast enough to preserve venue in the district where their client was initially detained.

John HughesSpecial Counsel, Litigation

This is an automated cite checker

Damien CharlotinPlumitif

The Enron corpus of 500,000 plaintext emails from 142 document custodians is a natural candidate for LLM assisted litigation preparation. Recent changes to the U.S. Federal Rules of Civil Procedure accelerate the meet and confer to a much earlier point. Over the course of an afternoon, Claude Opus 4.6 was guided through a preprocessed, deduplicated version of the corpus. Careaga, R. (2026). Preprocessed Enron corpus [Data set]. Zenodo. https://doi.org/10.5281/zenodo.18857652 The LLM extended. my previous network/semantic analysis to identify and classify communities of email users and identify tiers most likely to contain attorney-client communication or work product privileged records and the large residuum where sampling could serve. I am currently extending that work with DiscoveryGraph.jl to implement human review where attorney judgment is required. I'm finding that the algorithms so far appear overinclusive, bringing in administrivia such as "not able to attend weekly litigation update meeting."

Richard CareagaAnalytic Pragmatician

Collate is a browser-based tool for litigation lawyers that turns messy multi-reviewer feedback into a single view. Lawyers drop in several marked-up Word documents from counsel, partners, clients, and juniors; Collate parses comments, track changes, and inline edits, merging them into a paragraph-by-paragraph checklist with resolution status. Manual feedback from calls, emails, or meetings can be added and treated like extracted comments. It’s built to be a checklist and review aid, not an auto-merge tool — the lawyer stays in control and makes the edits in Word. Everything runs in the browser. A Rust engine compiled to WebAssembly parses DOCX files locally, and a React UI presents the collated feedback. A strict Content Security Policy blocks outbound network requests, so privileged documents never leave the machine and nothing is uploaded to any server. The tool works offline, and IT or compliance can verify this from the source code and CSP headers. Collate was built in about 90 minutes by a practising UK litigator using AI-assisted development. It supports inline diff display, wholesale paragraph insertions and deletions, multi-document merging via approximate paragraph matching, bulk resolution actions, search, and HTML/JSON export. The codebase is open source and includes over 100 automated tests across the Rust core and React frontend.

James Cockburnlawyer

CaseKit is a free, open-source desktop application that helps you organise a consumer dispute from first complaint to court hearing — entirely on your own computer. Upload your documents, and CaseKit sorts them into evidence folders, extracts key dates into a chronology, and walks you through the procedural steps of bringing or defending a small claim. Nothing leaves your machine: no cloud accounts, no subscriptions, no data harvesting. Your case files stay in a plain folder on your hard drive that you control — you can open them, move them, or delete them at any time without asking anyone's permission. If you choose to use the optional AI features for drafting or merits analysis, you bring your own API key and the requests go directly from your device to the provider — CaseKit never sees your key or your data. CaseKit does not provide legal advice, all decisions are your own. Casekit just helps you to organise, as well as to be realistic and informed. Whether you're representing yourself or preparing to instruct a solicitor, CaseKit saves you the most expensive thing in litigation: time. Self-representing litigants can use the procedural roadmap, letter templates, and court form links to navigate the process without paying for guidance on steps they can handle alone. If you're planning to instruct a solicitor, arriving at your first meeting with an organised bundle — documents categorised, chronology built, key issues identified — means you spend that meeting on strategy rather than on your lawyer reading through a carrier bag of unsorted paperwork at £300 an hour. Either way, the AI merits assessment gives you a frank, objective, structured view of the strengths and weaknesses of your position before you commit to a course of action. CaseKit also includes something no other consumer legal tool offers: a Citation Auditor that verifies whether legal citations actually exist. Paste any AI-generated legal text, an opponent's skeleton argument, or your own draft, and CaseKit extracts every case law citation, then checks each one against BAILII and the National Archives — the two public legal databases that hold virtually every reported judgment in England and Wales. It tells you instantly whether each cited case is real, whether the name matches, and flags anything suspicious. Don't be that litigant. CaseKit is still under development, do not rely on this tool yet.

James Cockburnlawyer

A Word-integrated desktop tool that allows users to manage, cite and export exhibits with minimal fuss. Inserted citations can be refreshed with one click even after amendments have been made (e.g. re-ordering of exhibit numbers, re-naming of existing exhibits etc). ExhiBytes also allows users to preview exhibits without opening, annotate exhibits with internal notes, and export bundles based on selected (or all) exhibits. File formats supported are generous: PDF, DOCX, DOC, XLSX, XLS, PPTX, PPT, ODT, ODS, ODP, RTF, TXT, PNG, JPG, JPEG, and EML. ExhiBytes runs locally on the user's desktop and does not require any API key calls.

Sze Yao TanState Counsel

A nifty web-based tool that allows for the calculation of court deadlines (for filings etc) based on various trigger events set out in the Singapore Rules of Court 2021. Results display with a calendar view, allowing the user to re-confirm the number of days counted and the actual deadline day.

Sze Yao TanState Counsel