BrowseAI Dev
未认领Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
安装
npx browseai-dev setup更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
13 个工具中显示 13 个
文档中列出的工具 (13)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
browse_answer
Full pipeline: search + extract + cite. depth: "fast", "thorough", or "deep"
browse_clarity
Anti-hallucination answer engine — three modes: prompt (prompts only), answer (LLM), verified (LLM + web fusion)
browse_compare
Compare raw LLM vs evidence-backed answer
browse_extract
Extract structured claims from a page
browse_feedback
Submit feedback on a result to improve accuracy
browse_open
Fetch and parse a web page into clean text
browse_search
Search the web for information on any topic
browse_session_ask
Research within a session (recalls prior knowledge)
browse_session_create
Create a research session (persistent memory)
browse_session_fork
Fork a shared session to continue the research
browse_session_knowledge
Export all claims from a session
browse_session_recall
Query session knowledge without new web search
browse_session_share
Share a session publicly (returns share URL)