344 个 · Agent 智能体 · 工具
代码智能 CLI——覆盖 34 种语言的函数级依赖图、为 AI agent 提供 34 工具的 MCP server、复杂度度量、架构边界强制、CI 质量门禁、git diff 影响分析（含 co-change 分析）、混合语义搜索。完全本地运行，无需 API key。Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.
开源的 AI Agent 真实 iPhone 控制方案：屏幕文本、点击/输入/滑动、自定义 XCTest runner、CLI + HTTP API + MCP、浏览器接管与可回放流程。Rust 编写，自托管于 macOS。Open-source real iPhone control for AI agents: screen text, tap/type/swipe, custom XCTest runner, CLI + HTTP API + MCP, browser takeover and replayable flows. Rust, self-hosted on macOS.
一个由 Jev 驱动的轻量路由器，用于模型、工具与 subagentA lightweight Jev-powered router for models, tools, and subagents
更便宜且更优秀的 Greptile 替代方案，运行在你自己的 GitHub Actions 上。Cheaper and better Greptile alternative runs on your own github actions.
为 Claude Code 和 Codex CLI 提供的自托管浏览器工作空间，集成 Docker 会话、终端、文件、Git 与用量跟踪。Self-hosted browser workspace for Claude Code and Codex CLI, with Docker sessions, terminal, files, Git, and usage tracking.
文档驱动的文献综述流水线，包含反幻觉验证阶段（基于 OpenAlex/Crossref/Semantic Scholar 进行确认或剔除）。Document-driven literature-review pipeline with an anti-hallucination verification stage (confirm-or-drop against OpenAlex/Crossref/Semantic Scholar).
Claude Code skill：在本地浏览器页面而非终端中运行 grilling design interview。Claude Code skill: run a grilling design interview on a local browser page instead of the terminal
LitLLM：面向科学文献综述的工具包。LitLLM: A Toolkit for Scientific Literature Review
白泽 —— 中国古代神话中通晓万物的瑞兽，如今化身为 Vibe Coding 助手。 一个开源的 AI Coding Agent CLI，支持多后端（DeepSeek / OpenAI 兼容 / Ollama 本地），具备工具调用、技能加载、子代理委派、上下文压缩、安全沙箱等完整能力。在终端即可与 AI 结对编程。
Promptfoo 的 GitHub Action。可用于测试 prompt、Agent 与 RAG；支持 LLM 的 AI 红队对抗、渗透测试与漏洞扫描；对比 GPT、Claude、Gemini、Llama 等模型的性能；通过简洁的声明式配置集成命令行与 CI/CD。The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversarial review.
在同一桌面工作区中汇聚所有编码 Agent。并行运行 Claude Code、OpenAI Codex、Cursor Agent 与 Grok。支持自带 CLI。Beta 期间免费。自 2026 年 9 月 21 日起开源（MIT）。Every coding agent in one desktop workspace. Run Claude Code, OpenAI Codex, Cursor Agent and Grok side by side. Bring your own CLI. Free during beta. Open source as of 21 September 2026 (MIT).
通过终端或 AI agent 检索并申请覆盖 7 个国家（🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷）约 4,700 个薪资透明的科技岗位——零依赖 Python CLI + MCP server + Claude Code 插件Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency Python CLI + MCP server + Claude Code plugin
RuvNet Brain——基于 Reuven Cohen（rUv）的 RuvNet 技术栈（RuVector/RVF、Ruflo、AgentDB、RuLake、SPARC 及 21 个构建块）为 Claude Code 提供一个可下载、源码溯源的"大脑"。通过单一 MCP 工具（search_ruvnet）让 Claude 立足真实源码，而不是脱离技术栈空想。RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.
面向 OpenCode 与 Claude 的轻量级持久记忆伴侣A lightweight persistent-memory companion for OpenCode & Claude
开源 AI CLI 与本地 MCP 服务器，连接 25 个 AI 客户端（包括 Claude Code、Cursor、Codex 和 ChatGPT）与 2000+ 模型和 API，支持 OAuth 与回滚Open-source AI CLI and local MCP server connecting 25 AI clients—including Claude Code, Cursor, Codex, and ChatGPT—to 2,000+ models and APIs, with OAuth and rollback.
ModeAtlas 2026：面向开发者的 AI 驱动代码仓库情报工具。ModeAtlas 2026: AI-Powered Repository Intelligence for Developers
PokePlus 2026：PokeMMO 冒险智能自动捕捉与对战机器人PokePlus 2026: Smart Auto-Catch & Battle Bot for PokeMMO Adventures
AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQLite.
Apple Silicon 上的本地计算机使用：通过 macOS Accessibility API 驱动，由 laya 实现设备端类型化决策，由 CUA-S1-FORMS 实现表单填写。Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API
Zorv AI — 安卓 Android 端开源 AI Agent 智能体助手。多模型对话、人格系统、记忆、语音全双工 TTS/STT、定时任务、可扩展工具链、飞书/QQ/微信接入。Kotlin + Jetpack Compose 开发。
MCP server，将 V8 JavaScript 运行时暴露为工具，供 Claude、Cursor 等 AI Agent 调用，支持通过 S3 或本地文件系统持久化堆快照，可直接接入现代 AI 开发环境MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
一款能停下来向你询问的浏览器工具。无论是 2FA 验证码、CAPTCHA，还是只有你才能做出的选择：它会在屏幕上向你询问，然后在你已登录的标签页中继续执行。40 个工具，支持任意 MCP client，MIT 许可。The browser tool that can stop and ask you. A 2FA code, a CAPTCHA, a choice only you can make: it asks on your screen, then carries on in the tab you were already signed into. 40 tools, any MCP client, MIT.
面向创意工具的 Skill 优先控制平面：共享 MCP/REST runtime、gateway、CLI、marketplace、安全与可观测性，覆盖工作室流水线。Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.
Anthropic Claude Certified Architect（CCAR-F）认证的非官方备考指南。涵盖 Agentic 循环、多 Agent 系统、子 Agent、MCP 服务器、hooks、工具路由、CLAUDE.md 层级、slash 命令、plan 模式与 Claude Code CI/CD 流水线。Unofficial study guide for Anthropic's Claude Certified Architect (CCAR-F) certification. Covers agentic loops, multi-agent systems, subagents, MCP servers, hooks, tool routing, CLAUDE.md hierarchy, slash commands, plan mode, and Claude Code CI/CD pipelines.
使用 Claude Code 进行医学学术写作Medical Academic Writing with Claude Code
ASTRA 的 Agent 层 —— 面向可复现研究的专用 skills、工作流执行与 HPC/容器管理。Agentic layer for ASTRA — dedicated skills, workflow execution, and HPC/container management for reproducible research
基于 AI 的学术同行评审助手。基于 LangGraph 构建，可核对引用与论点、标记无支撑断言、执行文献综述并推荐相关引用，帮助评审者与研究者更高效地评估严谨性AI-powered assistant for academic peer review. Built with LangGraph, this tool validates references against claims, flags unsupported assertions, performs literature reviews, and suggests relevant citations — helping reviewers and researchers assess rigor more efficiently.
持久化的多 agent 工作流编排——DAG 任务、git worktree、merge gate，兼具桌面端 + CLI + Slack。Persisted multi-agent workflow orchestration — DAG tasks, git worktrees, merge gates, desktop + CLI + Slack
OpenChronicle 是一个面向 LLM 的开源、自托管交互引擎，让对话具备持久性。它提供持久记忆、确定性任务调度与可审计的决策轨迹，避免工作因会话重置而丢失。设计上与 provider 无关，支持多种接口（CLI、Discord、MCP），并采用明确且注重隐私的路由策略。OpenChronicle is an open-source, self-hosted interaction engine for LLMs that makes conversations durable. It adds persistent memory, deterministic tasking, and auditable decision trails so work doesn’t reset each session. Provider-agnostic by design, it supports multiple interfaces (CLI, Discord, MCP) with explicit, privacy-aware routing.