[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-94517":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":21,"readmeContent":22,"aiSummary":23,"trendingCount":16,"starSnapshotCount":16,"syncStatus":24,"lastSyncTime":25,"discoverSource":26},94517,"harvey-labs","harveyai\u002Fharvey-labs","harveyai","A benchmark built to evaluate and improve agent capabilities for supporting legal work.",null,"https:\u002F\u002Fgithub.com\u002Fharveyai\u002Fharvey-labs","Python",964,186,13,12,0,148,57.82,false,"main","2026-08-24 04:01:22","\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Flab-hero.png\" alt=\"Harvey LAB\" width=\"100%\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>Legal Agent Benchmark (LAB): An open-source benchmark for evaluating agents on real legal work.\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fharveyai\u002Fharvey-labs\u002Ftags\">\u003Cimg alt=\"Latest version\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Ftag\u002Fharveyai\u002Fharvey-labs?display_name=tag&sort=semver&style=flat-square&label=version\">\u003C\u002Fa>\n  \u003Cimg alt=\"License: MIT\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green?style=flat-square\">\n  \u003Cimg alt=\"Legal practice areas\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flegal%20practice%20areas-24%20%2B%20contracting-0E7C7B?style=flat-square\">\n  \u003Cimg alt=\"Tasks\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftasks-1671-4F46E5?style=flat-square\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fharveyai\u002Fharvey-labs\u002Factions\u002Fworkflows\u002Fvalidate-task-schema.yml\">\u003Cimg alt=\"Test suite\" src=\"https:\u002F\u002Fgithub.com\u002Fharveyai\u002Fharvey-labs\u002Factions\u002Fworkflows\u002Fvalidate-task-schema.yml\u002Fbadge.svg?branch=main\">\u003C\u002Fa>\n\u003C\u002Fp>\n\nHarvey LAB is an open-source project aimed at benchmarking LLM agents' abilities to perform legal work in realistic environments.\n\nLAB consists of two parts: a dataset of *tasks* containing agent instructions, documents, and rubrics as well as an *execution harness* for running and evaluating agents against those tasks.\n\nLAB is an ongoing project and we expect to consistently add to and refine the task set and execution harness.\n\nRead the announcement post: [Introducing Harvey's Legal Agent Benchmark](https:\u002F\u002Fwww.harvey.ai\u002Fblog\u002Fintroducing-harveys-legal-agent-benchmark)\n\n## Getting Started\n\nStart with the full walkthrough in **[docs\u002Ftutorial.md](docs\u002Ftutorial.md)** — it takes one realistic M&A data-room assignment end to end: setup, task inspection, agent run, scoring, report review, and comparison dashboards.\n\n## Additional Documentation\n\n| Guide | Description |\n|---|---|\n| [Architecture](docs\u002Farchitecture.md) | Task model, harness, tools, adapters, reports, and sweeps |\n| [Evaluation Methodology](docs\u002Feval-strategies.md) | All-pass rubric scoring and LLM judge behavior |\n| [Contributing](CONTRIBUTING.md) | Add tasks, model adapters, evaluation improvements, and docs |\n\n## Citation\n\nIf you use Harvey LAB in your research, please cite it as:\n\n```bibtex\n@misc{harveylab2026,\n  title   = {Harvey LAB: The Legal Agent Benchmark},\n  author  = {{Harvey AI}},\n  year    = {2026},\n  version = {v1.0},\n  url     = {https:\u002F\u002Fgithub.com\u002Fharveyai\u002Fharvey-labs\u002Ftree\u002Fv1.0},\n  note    = {Announcement: \\url{https:\u002F\u002Fwww.harvey.ai\u002Fblog\u002Fintroducing-harveys-legal-agent-benchmark}}\n}\n```\n","Harvey LAB 是一个面向法律领域的大语言模型智能体能力评测基准，旨在评估和提升AI代理在真实法律工作场景中的表现。项目包含1671个法律任务数据集（覆盖合同审查、并购尽调等24+业务领域）及配套执行框架，支持自动化运行、多维度评分（含LLM裁判机制）与结果分析。技术上采用模块化设计，兼容多种模型适配器与工具集成，强调任务真实性与评估严谨性。适用于法律科技公司、AI研究团队及法学院开展法律智能体研发、模型选型与能力验证。",2,"2026-08-11 02:30:03","trending"]