AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
Universal LLM benchmarking harness for tool use, browser, mobile, coding, and long-horizon evals
翻译准备中
开发工具Python · ShellGitHub @Toloka自行安装运营者未确认
试用过了吗? 点一下就好,无需登录。
正在加载完整 README。 以下为已保存的摘录。
A benchmarking harness for evaluating tool-using LLM agents. Multi-turn agent/user loops, sandboxed execution, deterministic grading, and rich telemetry — across any provider via LiteLLM.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
A benchmarking harness for evaluating tool-using LLM agents. Multi-turn agent/user loops, sandboxed execution, deterministic grading, and rich telemetry — across any provider via LiteLLM.查看完整 README ↗