Legal AI & NLP
Models, pipelines, and applications for legal language.
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型
Open document intelligence platform, annotation plus LLM
Privacy-first local notetaker for confidential work
[中文法律大模型] DISC-LawLLM: an intelligent legal system powered by large language models (LLMs) to provide a wide range of legal services.
Local-first anonymisation before LLM use
LexNLP by LexPredict
:black_circle: A spaCy pipeline and model for NLP on unstructured legal text.
Benchmarking Legal Knowledge of Large Language Models
AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.
夫子•明察司法大模型是由山东大学、浪潮云、中国政法大学联合研发，以 ChatGLM 为大模型底座，基于海量中文无监督司法语料与有监督司法微调数据训练的中文司法大模型。该模型支持法条检索、案例分析、三段论推理判决以及司法对话等功能，旨在为用户提供全方位、高精准的法律咨询与解答服务。
Open-source collection scripts for open legal data from 110+ countries maintained by the Legal Data Hunter agent. Request your government's data source or contribute a script.
Taiwan judgment semantic retrieval CLI
67 debating agents, human gates, Apache 2.0
We curate a large corpus of legal and administrative data. The utility of this data is twofold: (1) to aggregate legal and administrative data sources that demonstrate different norms and legal standards for data filtering; (2) to collect a dataset that can be used in the future for pretraining legal-domain language models, a key direction in access-to-justice initiatives.
Claude skill encoding a Chinese-law contract review methodology: 30 contract types, 124 risk templates, and marked-up DOCX plus a structured legal opinion as output.
This is the repo for the LegalBench-RAG Paper: https://arxiv.org/abs/2408.10343.
Build one of these? Verify ownership through GitHub and take over your project's page: tagline, categories, maintainer's note.