jev-websearch-eval
anweat/jev-websearch-eval · anweat
Independent offline evaluation of the Bocha Jev decision model in a web-search evidence pipeline (vs. rule baseline and Laya): tasks, metadata-only snapshots, LLM-draft labels, judge outputs, reports
项目资料
基本信息
- Star
- 0
- 派生
- 0
- 语言
- JavaScript
- 许可证
- MIT
- 创建时间
- 2026-10-06
- 最近更新
- 2026-10-06
同一分类
还可以看看
模型与连接 · 技能open-designnexu-io🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.
模型与连接 · 技能archifytt-a1iTurn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
模型与连接 · 技能rufloruvnet🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated