1215 个 · AI 核心
企业级 SaaS API 的本地模拟器——涵盖 Slack、Gmail、Google Drive、GitHub、Jira、Notion、S3 等——具备真实的响应结构、分页、鉴权以及逐文档 ACL，运行于用户自提供的语料之上。A local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, pagination, auth and per-document ACLs, over a corpus you supply.
逐步学习 LLM 推理工程——从 KV cache、PagedAttention 和连续批处理，到 vLLM、SGLang 和 GPU。Learn LLM Inference Engineering step by step - from KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.
静态分析工具，可在所有主流编程语言中检测 1000+ 错误模式，并自动接入 AI coding agent 的质量护栏。Static analysis tool that catches 1000+ bug patterns across all popular programming languages, with auto-wiring into AI coding agent quality guardrails
Kelos——面向自主 AI 编程 Agent 编排的 Kubernetes 原生框架。Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.
Claude Code 的完整 AI 开发工具包。包含 106 个 skill、36 个 agent、171 个 hook。安装 `ork` 获取稳定版（v9.x），或安装 `ork-alpha` 获取每日发布的 v10 版本。The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
一种极简的硬件-软件架构，为大语言模型提供具有自感知回路的闭环物理具身。A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.
你的主动式个人 AI 助手与日常生产力伙伴 🌎Your proactive personal AI assistant & companion for daily productivity 🌎
招募 AI Agent：真金白银的真实赏金，每笔支付锚定公开账本。gofrantic.com 公告板。HELP WANTED: AI AGENTS. Real bounties, real money, every payout sealed to a public ledger. The notice board for gofrantic.com
纯 Go 实现的单文件 AI 记忆与知识图谱库及插件A pure-Go, single-file AI memory and knowledge graph library and plugin.
多 Agent 应用，支持并行会话、工具、记忆、工作流，覆盖桌面、终端与移动端。Multi-agent app for parallel sessions, tools, memory, workflows, desktop, terminal, and mobile.
开源 agent 评估与可观测性：在一个开放平台上追踪、评估并改进 LLM 应用。🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
面向 Forward Deployed Engineer 的第二大脑：在 discovery、交付与交接全过程中提供 engagement 记忆与执行 Skill。Second brain for Forward Deployed Engineers: engagement memory + execution skills across discovery, delivery, and handoff.
DeepSeek Harness 审批请求的 second-model AI 自动复核：只读复核子 Agent 返回结构化 allow/deny 判定及理由，默认 fail-closed，会话日志（approval/asked → autoReview/verdict → approval/decided）全程可审计。Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
Hermes Agent 的 Windows 端便携桌面版 — 100 个工具、图形界面、通过 LM Studio 加载本地模型、TTS、音乐、ComfyUI、工作流、工具创建器。无需安装、无需 Docker、无需管理员权限。Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.
一门关于现代 LLM 架构、训练与推理的实战课程，配有逐步 PyTorch 实现和可运行的 notebook。A hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.
AgenticX 是一个统一、生产就绪的多 Agent 平台——Python SDK + CLI (agx) + Studio server + Machi 桌面应用。具备 Meta-Agent 编排、15+ LLM provider、MCP Hub、分层记忆、头像与群聊、Skill 生态、安全沙箱和 IM 网关（飞书/微信）。AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
统一的 Agentic AI 与商业智能平台Unified Agentic AI and Business Intelligence Platform
一份配置即可统管所有 AI agents：跨项目跨会话可移植、内置精选写作/路由/skills、更安全（内置破坏性命令防护）One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).
DeepSeek Harness 的可验证研究报告引擎：内容寻址的 evidence ledger（claim-snapshot 绑定、防篡改），以及版本化 sealed 报告，含逐条 claim 的验证判定与 manifest-sealed 目录。Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.
本地优先的 MCP 网关。一个端口对接所有工具和所有 AI 客户端：惰性发现（节省约 90% token）、工具完整性校验与隔离、密钥存储于操作系统密钥链。Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
面向教育领域的人工智能（AI）与大语言模型（LLM）论文精选。Awesome artificial intelligence (AI) and large language model (LLM) for education papers.
多 agent 系统的可靠性层——无需 orchestrator 即可保持 agent 间协同。跨对话契约 + 漂移检测 + 黑盒记忆（无需 LLM 抽取）。Reliability layer for multi-agent setups — keep agents coordinating without an orchestrator. Cross-dialog contracts + drift detection + black-box memory (no LLM extraction).
自托管 AI 工作站：自主屏幕 Agent、三层神经路由、并行 Agent 集群、视频生成、4K/8K 升频、RAG、语音接口、60+ 工具执行引擎——全部在你的硬件上本地运行。The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video generation, 4K/8K upscaling, RAG, voice interface, 60+ tool execution engine — all running locally on your hardware.
开源的 Agent-Bot prompt 目录，覆盖 Grok Bot、Rakazo 及任何 Agent——botdirectory.ai。Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai
用于探索 Transformer 架构、张量及实时 LLM 推理的交互式 3D 可视化平台。Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.
[ICML 2026] effGen：让小型语言模型具备自主 Agent 能力[ICML 2026] effGen: Enabling Small Language Models as Capable Autonomous Agents
LLM7.io 提供单一 API 网关，可连接来自多家供应商的众多领先 AI 模型LLM7.io offers a single API gateway that connects you to a wide array of leading AI models from various providers.
[COLM 2025] 论文 Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale——大语言模型在动态用户画像与大规模个性化响应任务上的基准测试。[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
🔥一份关于最新视频推理任务、范式与基准的开源综述。🔥An open-source survey of the latest video reasoning tasks, paradigms, and benchmarks.
面向 AI Agent 的原生 Safari 浏览器自动化。通过 AppleScript 提供 97 个工具——零开销、保留登录态、后台静默运行。可直接替代 Chrome DevTools MCP，在 Apple Silicon 上 CPU 与发热降低 40-60%。Native Safari browser automation for AI agents. 97 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.
面向组织的开放、可自托管的 Agent 服务 —— 提供持久化、可回放的 Agent 会话、人工审批、受控凭证与记忆，运行于托管沙箱或自有硬件。Apache-2.0。Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.
前沿 AI 视频生成用于编程 Agent — Seedance、Runway、Veo、Kling 使用你自己的 API key，受硬性成本上限控制。CLI + MCP。Frontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard cost cap. CLI + MCP.