663 个 · Agent 智能体 · AI 核心
这份 AI 研究清单告诉你该"做什么不同"，而不仅仅是读什么——100+ 篇 2026 年顶会论文 → 50+ 条面向 AI Agent 构建者的生产实践要点。中英双语。The AI-research list that tells you what to DO differently, not just what to read — 100+ top-tier 2026 papers → 50+ production takeaways for AI agent builders. Bilingual EN/中文.
Warzone2100 的 Skirmish AI 机器人Skirmish AI bot for Warzone2100
桌面端 AI 伴侣，集成 Live2D 形象、自主编码 Agent（AgentLoop）、语义记忆与确定性主动引擎——真实进程沙箱（bwrap）、权限门控工具执行、local-first（SQLite + ONNX）。Desktop AI companion with Live2D avatar, autonomous coding agent (AgentLoop), semantic memory, and a deterministic proactivity engine — real process sandboxing (bwrap), permission-gated tool execution, local-first (SQLite + ONNX).
0n1x——Agent 执行证明（Proof of Agent Execution）。面向 AI Agent 的中立、签名式信任层：付款前先验证，签名的是事实而非判断。AI Agent 领域的 Carfax。0n1x — Proof of Agent Execution. The neutral, signed trust layer for AI agents: verify before you pay, signed facts not judgments. The Carfax for AI agents.
MeetMaxxing 是一个多 Agent AI 会议副驾，将在线会议转变为智能、协作的体验。专用 AI Agent 处理实时辅助、会议摘要、语义记忆、跟进邮件和智能日程——通过 Agent-to-Agent 通信协作，而非单一单体 LLM 工作流。MeetMaxxing is a Multi-agent AI meeting copilot that transforms online meetings into intelligent, collaborative experiences. Specialized AI agents handle live assistance, meeting summaries, semantic memory, follow-up emails, and smart scheduling — collaborating through Agent-to-Agent communication instead of one monolithic LLM workflow.
面向 AI coding agent 的终端多路复用器：一个键盘驾驶舱管控整支集群，配备工作项、任务队列与单面板资源上限。A terminal multiplexer for AI coding agents: one keyboard cockpit for the whole fleet, with work items, a task queue, and per-panel resource caps.
2026 终极 AI 记忆栈：面向 LLM 的本地优先 Rust MCP2026 Ultimate AI Memory Stack: Local-First Rust MCP for LLMs
证据门禁式 Coding Agent 编排器：冻结任务、独立验证、绑定摘要的评审、仅草稿可发布。Evidence-gated orchestration for coding agents: frozen tasks, independent verification, digest-bound review, draft-only publication. 证据门禁式 Coding Agent 编排器。
比特币元宇宙——主权数字土地上的主权 AI Agent。The Bitcoin Metaverse — Sovereign AI agents on sovereign digital land.
为 AI 编程 agent 构建 Claude Code prompt 模板，包含系统 prompt、工具 prompt、记忆管理与多 agent 协调。Build Claude Code prompt templates for AI coding agents, with system prompts, tool prompts, memory, and multi-agent coordination
🤖 为 Alrouf Lighting 提供 AI 驱动的 RFQ 自动化处理平台，集成 CRM 流程以提升运营效率🤖 Automate RFQ handling with our AI-powered platform, integrating CRM processes to streamline operations and enhance efficiency for Alrouf Lighting.
面向 CLI 编码 Agent 的桌面工作空间。可并行运行 Claude Code、Codex、OpenCode 和 Gemini CLI，每个任务使用独立的 git worktree。MIT 协议，local-first。A desktop workspace for CLI coding agents. Run Claude Code, Codex, OpenCode and Gemini CLI side by side — each task in its own git worktree. MIT, local-first.
开源、自托管的 Claude Code 与 opencode 客户端。Agent 在你自己的 Linux 主机或 Mac 上的真实 tmux 中运行，可通过桌面、手机或浏览器经 HTTPS 远程操控。Open-source, self-hosted Claude Code and opencode client. Agents run in real > tmux on your own Linux box or Mac, and you drive them from desktop, phone or > browser over HTTPS.
MCP 桥接，让 Claude Code 和其他宿主将实现工作委托给 OpenAI Codex CLI。MCP bridge that lets Claude Code and other hosts delegate implementation to the OpenAI Codex CLI
Agentic 流水线，检索 arXiv、Semantic Scholar 与 Hugging Face Papers，基于每篇论文自身的"局限性与未来工作"章节产出未来工作思路报告，并对缺少该章节的论文给出明确标注的推断分级。通过 Ollama 完全本地运行。Agentic pipeline that searches arXiv, Semantic Scholar, and Hugging Face Papers, then produces a report with future work ideas grounded in each paper's own Limitations and Future Work sections, plus a clearly labeled inferred tier for papers without one. Runs fully locally through Ollama.
📄 面向 AI Agent、RAG、知识图谱的每日论文发现 —— 覆盖 arXiv + HuggingFace + Papers With Code📄 Daily paper discovery for AI Agent, RAG, Knowledge Graph - arXiv + HuggingFace + Papers With Code
企业级数字支付平台：Java 21 / Spring Boot 3 微服务、Kafka 事件驱动、六边形（端口与适配器）架构，由专业 AI Agent 团队以 spec 驱动并编排，包含完整 CI/CD、GitOps 和供应链安全。Enterprise-grade digital payment platform: Java 21 / Spring Boot 3 microservices, Kafka event-driven, hexagonal (ports & adapters) architecture, spec-driven and orchestrated by a team of specialized AI agents. Includes full CI/CD, GitOps, and supply-chain security.
Codex Autonomous Objective Loops 2026：强制审查与验证的 AICodex Autonomous Objective Loops 2026: AI with Mandatory Review & Verification
📄 从任意网站提取面向 AI Agent 和 LLM 的文档，通过便捷访问 llms.txt 和 install.md 文件简化自动化工作流。📄 Extract documentation for AI agents and LLMs from any website, simplifying automation workflows with easy access to llms.txt and install.md files.
一款将模型命令沙箱化，并使用可编辑状态机处理长时间任务的编码 AgentA coding agent that jails model commands and uses editable state machines for long-running tasks
OWNEX——自主工作操作系统（Autonomous Work Operating System）：机会发现、安全自动化、Agent 编排、本地优先 AI 路由、收入情报。Python/FastAPI + Vue 3 + Tauri。OWNEX — Autonomous Work Operating System: opportunity discovery, security automation, agent orchestration, local-first AI routing, revenue intelligence. Python/FastAPI + Vue 3 + Tauri.
AI 驱动的 Monorepo 2026：设计系统、React 应用、Fastify API 与 Pulumi IaC。AI-Powered Monorepo 2026: Design System, React Apps, Fastify APIs & Pulumi IaC
一个通过自博弈掌握 LLM 工具调用的 Python 库A Python library for LLM tool call mastery through self play.
与你的 coding agent 语音对话，它会回复。为 Claude Code、Cursor 及任何 MCP 客户端提供 local-first 语音 I/O（MCP tools + Agent Skill）。🎙️ Talk to your coding agent. It talks back. Local-first voice I/O (MCP tools + Agent Skill) for Claude Code, Cursor and any MCP client.
面向飞书/Lark 的开源 AI 辅助入职方案：可配置工作流、文档 OCR 与审阅、Bitable 同步、提醒功能，以及零凭证 Demo。Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-credential demo.
Agent 中立的自主、协作与能力编排 harness。Agent-neutral autonomy, collaboration, and capability orchestration harness.
一道 Python 守门机制：在不分类提示词的前提下，阻止不可信的 agent 数据去构造敏感的工具调用参数。A Python gate that prevents untrusted agent data from authoring sensitive tool-call arguments—without classifying prompts.
基于 Clean Architecture 的模块化网络爬虫——wreq TLS 指纹识别、RAG 导出、MCP server、TUI、AI 语义清洗，配备 1,337 项测试并通过 Miri 验证。Modular web scraper with Clean Architecture — wreq TLS fingerprinting, RAG export, MCP server, TUI, AI semantic cleaning. 1,337 tests, Miri verified.
一次编写 AI Agent 知识，编译输出为所有 Agent 配置格式——CLAUDE.md、AGENTS.md、.cursor/rules 等。Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.
让 AI Agent 从 PDF（发票、报告、对账单）中提取文本和表格的 MCP server。MCP server that lets AI agents extract text and tables from PDFs: invoices, reports, statements.
通过实战教程构建有效的 AI 评测，使用真实 agent 提升生产系统技能🎯 Build effective AI evaluations through a hands-on tutorial, using a realistic agent to enhance your production system skills.
在你信任它们的静默之前，先证明它们仍然看得见的 hook。为你的编码 Agent 编写的检测器提供配对的正/负对照。Hooks that prove they can still see before you trust their silence. Paired positive/negative controls for the detectors your coding agent writes.
AI 增强的 IT 运维工作台——规格驱动、多提供商、本地优先，将事件与服务请求转为带 KB 引用的摘要，配备可审计会话、PII 脱敏与沙箱化操作。AI-augmented IT ops workbench — spec-driven, multi-provider, local-first. Turns incidents and service requests into KB-cited summaries with auditable sessions, PII redaction, and sandboxed actions.
AI DeFi Agent 的执行前守卫 API —— <300ms 返回二元判定，通过 x402 支付 0.01 USDC。Pre-execution guard API for AI DeFi agents — binary verdict in <300ms, $0.01 USDC via x402
AI 编码 Agent 的本地优先任务控制中心：可见的 PTY 工作流、隔离的 Git worktree、后端主导的审查、精确 OID 合并，以及不可变的完成回执。Local-first mission control for AI coding agents: visible PTY work, isolated Git worktrees, backend-owned review, exact-OID merge, and immutable completion receipts.
AI 原生 Google Maps 地点与评论情报——让你有备而来。任意语言的自由文本输入 → AI 规划抓取完整评论历史 → Gemini 生成价格、硬性事实与风险标记报告。CLI + Web 应用 + 运行时可切换推理模型。AI-native Google Maps place + review intelligence — walk in armed. Free-text in any language → AI-planned scrape of FULL review history → Gemini price/hard-facts/red-flag reports. CLI + web app + runtime-switchable reasoning model.