{"slug":"webarena","name":"webarena","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"stale","officialUrl":"https://webarena.dev","repo":"https://github.com/web-arena-x/webarena","latestVersion":"v0.2.0","latestRelease":"2023-10-21","stars":1622,"starsAsOf":"2026-10-09","description":"Code repo for \"WebArena: A Realistic Web Environment for Building Autonomous Agents\"","descriptionZh":"真实网站环境 agent 基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-09","topics":["agent","nlp"],"language":"Python","lastPush":"2025-11-26","formerly":null,"packages":[],"recentVersions":[{"version":"v0.2.0","date":"2023-10-21","prerelease":false,"url":"https://github.com/web-arena-x/webarena/releases/tag/v0.2.0","source":"GitHub Release"},{"version":"v0.1.0","date":"2023-08-23","prerelease":false,"url":"https://github.com/web-arena-x/webarena/releases/tag/v0.1.0","source":"GitHub Release"}],"alternatives":["osworld","promptfoo","openai-evals","deepeval","ragas","lm-evaluation-harness","opencompass","swe-bench"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"开源大库收录：真实网站环境 agent 基准","sources":["oss"],"record":"https://aimap.page/api/v1/software/webarena.json","pages":{"en":"https://aimap.page/en/software/webarena/","zh-hans":"https://aimap.page/zh-hans/software/webarena/"}}