# PKU-YuanGroup/ChatLaw

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

Repository: https://github.com/PKU-YuanGroup/ChatLaw
Canonical: https://ross.abutalabs.com/products/chatlaw
Homepage: https://chatlaw.cloud/
License: AGPL-3.0
License Family: copyleft
Last push: 2025-01-04T15:29:26+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 84
- inputs: {"age_days": 1183, "days_push": 606, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7588, forks 619 (observed 2026-08-28T04:10:01.806071+00:00)

## What it is
ChatLaw is a family of large language models and a multi-agent legal assistant tailored for Chinese legal language processing, built on a Mixture-of-Experts architecture with knowledge graph integration. It includes specialized models such as ChatLaw2-MoE, ChatLaw-13B/33B, and a Text2Vec model for matching queries to relevant legal statutes.

## Use cases
- answer Chinese legal questions with an LLM
- build a legal consultation chatbot
- match user queries to relevant Chinese statutes
- research legal QA model performance on Lawbench
- deploy a multi-agent legal assistant with reduced hallucination

## When to choose
- you need a model specialized in Chinese legal language and statutes
- you want a multi-agent legal assistant with knowledge-graph grounding
- you need legal text similarity matching trained on court decisions

## When to avoid
- you need legal assistance outside Chinese jurisdiction or language
- you need a production-ready commercial product (AGPL-3.0 and research nature)
- you lack GPU resources to run 13B+ or MoE models

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, rag, agent-framework, nlp, chatbot
- domain: large-language-models, artificial-intelligence, legal
- platform: python, self-hosted
- tags: chinese-legal, mixture-of-experts, multi-agent, knowledge-graph, legal-qa, text2vec, huggingface-models, natural-language-processing, ai-agents, gpu

## Member repositories
- PKU-YuanGroup/ChatLaw (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:01.806071+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:36:53.586882+00:00, confidence not recorded.
  - readme: https://github.com/PKU-YuanGroup/ChatLaw (fetched 2026-08-28T04:10:01.806071+00:00, sha a06d509eeffa)
- Data as of 2026-08-30T08:39:29.467469+00:00.