Legal Tech Python Packages

python-redlines

Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies

python-redlines-docxodus

Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies

mcp-taiwan-legal-db

台灣司法院判決 + 全國法規資料庫 MCP server · Query Taiwan legal data from any MCP AI agent

jubarte-redlines

Word-faithful DOCX redlines and rendering without Word: a Rust engine with a Mac app, in-browser wasm, and Python and Node bindings. Scored against Microsoft Word.

python-redlines-ooxmlpowertools

Open-source DOCX comparison tool to generate native Word tracked changes (redlines) in Python without MS Word dependencies

hermes-legal-advisor

Free, multi-provider AI contract analysis. Scores risk, suggests redlines, gives a sign/negotiate/reject verdict. Works with Groq/Gemini free tiers or fully offline, no API key required.

jlawcite

Open, deterministic citation graph & search index of Japanese statutory law — 8,998 laws down to article/paragraph/item · 1.4M resolved citations · jlawcite CLI (lookup, BM25, graph walk) + MCP server + explorer

taiwan-legal-deid

De-identification for Taiwanese legal documents: realistic pseudonyms with a reversible mapping, on CPU

docx-redline

docx-redline is a production-grade Python library for creating tracked changes (redlines) in Word documents (.docx files). It builds on python-docx and lxml to write real OOXML revision markup that works natively in Word, LibreOffice, and Google Docs.

dd-agents

Legal flags a risk. Finance flags another. We connect and cite. Open-source forensic M&A due diligence: 13 AI agents read your data room across 9 domains (Legal, Finance, Commercial, Tech, Cyber, HR, Tax, Regulatory, ESG), cross-reference findings no single reviewer connects, and trace every one to an exact page & quote.

kaos-agents

Agentic runtime for KAOS: Runner, SessionMemory (with reflexion lessons), 5 patterns (Chat/PlanExecute/Research/Findings/Router), 14 MCP tools, FastAPI REST API, audit-trail telemetry recorder.

fedlex-mcp

MCP server for Swiss federal law (Fedlex) — search the SR, monitor legal changes, and query BBl/treaties via Claude Desktop or Claude.ai

legalize-cli

사람과 에이전트를 위한 한국 법령·판례·행정규칙·자치법규 조회 CLI·MCP 도구

twlaw

以本機 SQLite 查詢全國法規資料庫，支援中文全文檢索與章節層級重建 · Taiwan laws & regulations, queryable offline

codify-core

Turn a statute book into Akoma Ntoso: acquisition, transcription, anchor-driven structuring, retrieval and comparison for legal text. Apache 2.0.

contractex

Open-source Python library for legal document intelligence: privacy enforced in code, quality measured.

krokai

Your AI quoted a law. Is the quote real? KrokAI Law checks every quotation in your documents against the actual source text on your own disk, then sends the same question to several models and runs their quotations through the same check. Offline, no API key.

emsal-mcp

Dayanak (eski adı emsal-mcp): Türk hukukunda atıf doğrulamalı karar ve mevzuat araştırması için MCP sunucusu

compliancelint

EU AI Act compliance: scan, attest, document — from your IDE. Scanner catches code-verifiable violations, AI collects evidence for hybrid obligations, Human Gates capture pure attestations. Source-available (BSL 1.1), MCP-native, audit trail included.

veqtor-mcp

Veqtor MCP: local, open-source tools for comparing Word contract drafts and creating tracked-change counterproposals with Claude.

swiss-courts-mcp

MCP Server for Swiss court decisions via entscheidsuche.ch - BGer, BVGer, BStGer + 26 cantonal courts

courtlistener-cli

Python CLI for the CourtListener REST API v4 — case law, PACER dockets, judges, oral arguments, financial disclosures & citations, with batch processing and XLSX/CSV/JSON export. Ships as a Claude/Codex/Gemini skill.

anonymize-mcp

MCP server pro NLP nástroje ÚFAL MFF UK (NameTag, MasKIT, PONK) — česká právní AI: anonymizace, NER, čitelnost

contractguardian

AI agent that reads the fine print so you don't have to. Upload any contract → get red flags, unfair terms, and plain-English explanations in seconds.