by chuanruihu · Agent Tool · ★ 81
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Level-Navi Agent This repository is the official repository for the paper Level-Navi Agent: A Benchmark and Framework for Chinese Web Search Agents. English | 中文 🌐 Project Introduction Level-Navi Agent is an open-source, general-purpose web search agent framework where any open or closed-source model can be deployed. Our agent is capable of breaking down and understanding complex questions, iteratively searching for information on the internet step by step, until it can answer the user's original question. Framework of Level-Navi Agent To comprehensively evaluate the performance of various models on web search tasks, we provide an open-source dataset - Web24 Dataset. The total number of samples in our dataset is 481, and all questions come from five major domains: finance, gaming, sports, movies, and events. Our classification comes from scenarios that people usually search for on the internet. To avoid interference from the model's internal knowledge to the framework, the main source of our dataset is news (before December 2024), and we ensure that there are credible information source links. Questions are divided into simple, conditional, c
| Stars | 81 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 60.5024233451132/100 |
| Last Updated | 2024-12-27 |
| Created | 2024-12-18 |
| Platforms | browser, python |
| Est. Tokens | ~1168k |
Looking for a Level-Navi-Agent-Search alternative? If you're comparing Level-Navi-Agent-Search with other agent tool tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strate
Power rename/refactor tool (now with agent skill support!)
Explore other popular agent tool tools:
Level-Navi-Agent-Search is The Level-Navi Agent, a framework that requires no training and utilizes large language models for deep query understanding and precise search operations. The repo includes benchmarks, datasets, and t. It is categorized as a Agent Tool with 81 GitHub stars.
Level-Navi-Agent-Search is primarily written in Python.
You can find installation instructions and usage details in the Level-Navi-Agent-Search GitHub repository at github.com/chuanruihu/Level-Navi-Agent-Search. The project has 81 stars and 11 forks, indicating an active community.
The top alternatives to Level-Navi-Agent-Search on Agent Skills Hub include tutor-skills, lenny-skills, repren. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.