Sign in

Repository Index

132,241 visible repositories in the index

Tags: LLM tools
Tags

A repository shows when it has any selected Tag.

Clear Tags
Filters

Filters

Clear all filters

3,145–3,168 of 3,504 · Most stars

这是 Claude Code 的 CLI 客户端主体(src/ 目录),即整个终端交互层的源码。具体包含: 1. CLI 入口与命令解析 — main.tsx(4684行)、entrypoints/(CLI 模式、SDK 模式、MCP 模式) 2. 终端 UI 渲染 — components/(144 个组件,用 React + Ink 渲染终端界面) 3. 工具系统 — tools/(43 个工具,Bash、文件读写编辑、Grep、Glob、Web 搜索等) 4. API 通信层 — services/api/(与 Anthropic 后端通信) 5. MCP 协议 6. 多 Agent/Team 协作 l 7. 认证与策略 8. 辅助服务 等

[ICLR 2025] FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

  • mllm
  • ifdl

The Clay Foundation Model - An open source AI model and interface for Earth

  • earth-observation
  • foundation-model
  • sentinel-2
  • sentinel-1

CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台,支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强,以及可扩展的 ReAct Agent / Subagent 工具体系,帮助厨房新手轻松成为“烹饪英雄”。

  • ai-chatbot
  • cooking-assistant
  • langchain
  • milvus

Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support ( rkllm )

  • ai
  • client-server
  • ia
  • llm

🧿 AutorizePro是一款强大越权检测 Burp 插件,通过增加 AI 辅助分析 && 进一步优化检测逻辑,大幅降低误报率,提升越权漏洞检出效率。 [ AutorizePro is a authorization enforcement detection extension for burp suite. By adding Ai-assisted analysis, it significantly reduces the false positive rate and improves the efficiency of vulnerability detection.