1052 个
Caura（前身 MemClaw）——面向 AI Agent 集群的受治理共享内存。多 Agent、多租户、原生 MCP。支持信任分级、keystone 策略、审计日志、知识图谱、自改进检索。Apache 2.0。Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
面向 AI Agent 的上下文工程。token 消耗减少约 80%。解决工具过载问题。内置进程内 BM25 与语义检索的 Skill 与 memory。支持渐进式披露（Progressive Disclosure）。无需向量数据库。Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
生产级 Go SDK，用于构建具备长期记忆、知识检索与语音能力的 AI agent，可作为库、守护进程或实时管道运行。Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.
面向你的 AI Agent 的开源控制平面。连接工具、雇佣 Agent、追踪每一个 token 与每一分钱。Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar
嵌入式 Agent，让客户用于自动化工作、构建视图并连接其工具。Embedded agents your customers use to automate work, build views, and connect their tools.
预训练基础推荐模型论文清单Paper List of Pre-trained Foundation Recommender Models
最佳的静态 AI 文本 humanizer。两个基于研究的、与 LLM 无关的 Skill，让 AI 写作听起来自然且具亲和力。九大杠杆，50+ 同行评审来源，覆盖 2024-2026 年检测文献。Best static AI text humanizer. Two research-grounded LLM-agnostic skills that make AI writing sound human and relatable. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature.
Qwen3.8-27B 在单卡 RTX 3090 上使用 vLLM 部署：64 并发下约 1,000 tok/s（int8 张量核心 GEMM、fp16 DeltaNet 状态），默认采样下单用户约 114 tok/s/贪心约 124 tok/s（MTP 草稿、自输出草稿词表、校准 int4 lm_head、split-KV 校验注意力），150k–262k 上下文；附带补丁、重新量化脚本与基准测试Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks
"Humanizer" 规则集，让 AI 文本更锐利、具备 genre 感知能力，包含具体锚点与 self-auditing 工作流"Humanizer" rules that make AI text sharper, genre-aware, with concrete anchors and self-auditing workflow
StarWhisper 天文 LLMs、StarWhisper Telescope、Virtual-GOTTA，以及面向 embodied observing workflow 的天文定制研究 skills。StarWhisper astronomy LLMs, StarWhisper Telescope, Virtual-GOTTA, and astronomy-adapted research skills for embodied observing workflows
仓库级代码生成与 Issue 修复必读论文 🔥Must-read papers on Repository-level Code Generation & Issue Resolution 🔥
决定你的 AI 编码 Agent 阅读哪些内容，并保留凭证。每次裁剪都可逐字节恢复，从不杜撰结果，所有数据从你自己的语料库回放。Decides what your AI coding agent reads, and keeps receipts. Every cut is recoverable byte for byte, it never invents a result, and the numbers are replayed from your own corpus.
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 🌎
关于构建 agent 的、基于源码佐证的架构笔记。Source-backed architecture notes on building an agent
将任意网站转换为面向 AI agents 的精简 CLI，仅用数百 token 而非数万个 token 即可浏览网页Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.
[TOSEM 2026] 大语言模型在自动化程序修复中的系统文献综述[TOSEM 2026]A Systematic Literature Review on Large Language Models for Automated Program Repair
🪢 Langfuse 文档——Langfuse 是开源 LLM 工程平台，提供可观测性、评估、Prompt 管理、Playground 与指标，用于调试与改进 LLM 应用🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps
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.
ServiceNow MCP server：450+ 工具与 26 项 AI 能力，适配任意 AI（Claude、ChatGPT、Gemini、Cursor、Copilot）。多传输（stdio、SSE、HTTP）、A2A、动态 schema 发现、默认只读。免费且源代码可用，属于 NowAIKit 套件。ServiceNow MCP server: 450+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic schema discovery, read-only by default. Free and source available. Part of the NowAIKit suite.
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).
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.
DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF）
Opptrix——AI 驱动的全球多市场投研工作台 | 面向中国 A 股的开源 LLM 投研助手。170+ MCP 工具、因子筛选、回测、自选股与 Electron 桌面端。TypeScript · React · Fastify monorepo。Opptrix — AI驱动的全球多市场投研工作台 | Open-source LLM research assistant for China A-shares. 170+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.
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.
[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
Google Deep Search 的实现，支持 1000+ 篇参考文献、本地推理、使用 RAPTOR 与抓取会话对话以及报告生成。An implementation of Google Deep Search with support for 1000+ references, local inference, chatting with your scraping session using RAPTOR, and report generation.
AI 驱动的 CLI 编码 Agent，内置 20+ 工具，支持 MCP 与多模型提供商。AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers
Qwen3.8 27B 在 SGLang 上运行于 DGX SparkQwen3.8 27B on SGLang for DGX Spark
面向 user-aware Agent 的开源记忆与上下文方案：作用域化记忆、来源追溯、检索质量、纠错、边界、评测，以及 MCP/HTTP 访问能力。Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
Semantic Scholar API 的 FastMCP 服务器实现，提供学术论文数据、作者信息及引用网络的全面访问。A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
一门实战课程，用 PyTorch 从零构建现代 LLM，包含 26 个可运行的 Jupyter Notebook，涵盖 tokenizer、attention、MoE、RLHF、推理、评估和蒸馏。A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.