Open Source Legal Software.
Every project is a real GitHub, Codeberg, or Hugging Face repository, with stats refreshed from its source. One listing per repo, reviewed by the community, claimed by its maintainer.
LegalSummarization An MTEB dataset Massive Text Embedding Benchmark The dataset consistes of 439 pairs of contracts and their summarizations from https://tldrlegal.com and https://tosdr.org/. Task category t2t Domains Legal, Written Reference https://github.com/lauramanor/legal_summarization How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: import mteb task =… See the full description on the dataset page: https://huggingface.co/datasets/mteb/legal_summarization.
MyCase MCP. Connect Claude to your MyCase legal practice management system. Ask Claude to look up cases, find contacts, check your calendar, review billing — all without leaving your conversation.
OpenRouter for legal work: vendor-neutral, benchmark-grounded skills that route each legal task (drafting, extraction, research, review, translation) to the right LLM. AGPL-3.0.
MCP server for FOLIO, the Federated Open Legal Information Ontology
Develop a Romanian legal domain Large Language Model (LLM) using pre-trained model and fine-tuning on legal texts. The fine-tuned model is available on Hugging Face.
Dataset Card for Free-Law-Project/opinions-synthetic-query-512 This dataset is created from the opinions-metadata, and used for training the Free Law Project Semantic Search models, including Free-Law-Project/modernbert-embed-base_finetune_512. Dataset Details The dataset is curated by Free Law Project by selecting the train split from the opinions-metadata dataset. The dataset is created for finetuning encoder models for semantic search, with 512 context window.… See the full description on the dataset page: https://huggingface.co/datasets/freelawproject/opinions-synthetic-query-512.
Attorney-grade negotiation playbooks for US commercial contracts, clause by clause. Open reference from Vaquill (vaquill.ai).
Seven Polish legal databases plus three EU sources, behind four MCP tools instead of forty-two.
MCP server for Polish tax interpretations (KIS/MF) via EUREKA (eureka.mf.gov.pl). 550k+ documents, 517k+ individual tax interpretations.
Open map of every legal-data source in 25 MENA jurisdictions — gazettes, consolidated legislation, apex courts, regulators.
MCP connector for Singapore Statutes Online
Local-first AI document intelligence for legal case management. 14 MCP tools, semantic search, OCR, and a draft editor — all running on your machine.
Judge-level court filing rules, court holidays, and privacy enforcement data for US courts, as an MCP server. Hosted at mcp.courtrules.app
Donna does the work you bill for. Open-source TX family-law assistant. MIT. Forked from Mike.
Free OSS cite verifier for legal briefs. Catches the hallucinated case before the judge does.
A Claude Code skill that drafts a complete USPTO provisional patent application from a technical disclosure or IP analysis document.
An MCP server to include the BetterCallClaude framework as MCP in Claude Desktop and Cowork
Build one of these? Verify ownership through GitHub and take over your project's page: tagline, categories, maintainer's note.