DATGEN:AI 驱动的多 Agent 研究助手,自动完成假设生成、数据分析与报告撰写。DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.
趋势榜
实时增长榜 · 周综述每周日由 spark 生成
按日期回看
2026-09-16 新收录仓库 14 个
Status Trio — 一款原生 macOS 应用,将 Wi-Fi、电池和音量合并为一个紧凑且可配置的状态图标,可置于菜单栏、Dock 或两者皆可,灵感来自 iPhone Duo 的组合状态栏。Status Trio — a native macOS app that combines Wi-Fi, battery, and volume into one compact, configurable status icon for the menu bar, the Dock, or both, inspired by the iPhone Duo combined status bar.
白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。
Super Smash Bros. Melee(NTSC-U 1.02)的原生 PC 移植版,基于 aurora 上的 doldecomp/melee 构建。不含游戏数据,请自备光盘。Native PC port of Super Smash Bros. Melee (NTSC-U 1.02), built from doldecomp/melee on aurora. No game data; bring your own disc.
腾讯 CodeBuddy 账号池管理控制台 + OpenAI 兼容反代网关。扫码纳管账号、自动签到、多密钥分发、IP 管控、调用日志与用量统计。UI 对标 linux-do/cdk。
YuE2 音乐生成,以及面向 ComfyUI 的可编辑钢琴卷帘界面。YuE2 music generation and an editable piano roll for ComfyUI
本地优先的桌面工作空间,用于持久化 AI 队友。支持 Codex、Claude、Grok 在专属工作空间中运行,具备任务队列、文件共享、浏览器控制与 Agent 间协作。A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
AI Bro——一个 local-first 的工作空间,用于 AI 对话、源链接知识与任务管理。AI Bro — a local-first workspace for AI conversations, source-linked knowledge, and tasks.
一个开源、agent-native 的多模态 AI 生成平台,基于 DeepSeek Harness 构建。每次交互都存在于 agent 对话与无限画布中,统一了创作、生成与编辑。An open-source, agent-native platform for multimodal AI generation, built on DeepSeek Harness. Every interaction lives in agent conversations and an infinite canvas, unifying creation, generation, and editing.
发现最重要的引用论文——按影响力、相关性和影响度排序Discover the citing papers that matter most — ranked by impact, relevance, and influence
ChatGPT 风格 AI 助手,面向 UET Taxila 学生——通过 RAG 基于真实大学数据回答招生/学费/课程问题,而非猜测。采用 Next.js、Convex 与 multi-LLM 路由。ChatGPT-style AI assistant for UET Taxila students - answers admissions/fees/courses questions using real university data via RAG, not guessing. Next.js, Convex, multi-LLM routing.
Claude Code Skill:在信任测试之前,先证明它能失败——破坏被测对象,确认用例因正确的原因变红,再恢复。MIT 协议。Claude Code skill: prove a test can fail before trusting it — break the subject, confirm red for the right reason, restore. MIT.
2026-09-16 增长榜定格 当日周增 Top 20
| 名次 | 名称 | 方向 | 周增 | Stars |
|---|---|---|---|---|
| 1 — | odysseus-dev/odysseus | Agent 智能体 | +152,621 | 84,138 |
| 2 — | lnkiai/m3e-canvas | 工程化 | +11,186 | 3,871 |
| 3 — | anywhere-labs/deepseek-harness-desktop | 评测基准 | +8,281 | 13,495 |
| 4 — | stablyai/orca | Agent 智能体 | +5,299 | 47,228 |
| 5 — | s1dashu/ip-as-logo-skill | Agent 智能体 | +4,646 | 3,727 |
| 6 — | MiniMax-AI/MiniMax-H3 | LLM 基础设施 | +4,445 | 4,611 |
| 7 — | diegosouzapw/OmniRoute | Agent 智能体 | +4,343 | 53,672 |
| 8 — | holaboss-ai/holaOS | Agent 智能体 | +3,798 | 9,436 |
| 9 — | safishamsi/graphify | 数据与向量库 | +3,752 | 76,856 |
| 10 — | NousResearch/hermes-agent | Agent 智能体 | +3,386 | 230,735 |
| 11 — | zhu1090093659/dsh-web-ui | 评测基准 | +3,318 | 4,541 |
| 12 — | firecrawl/firecrawl | RAG 检索增强 | +2,975 | 165,271 |
| 13 — | firecrawl/anydoc | 工程化 | +2,870 | 13,720 |
| 14 — | koala73/worldmonitor | Agent 智能体 | +2,239 | 82,478 |
| 15 — | yjh051108/dsh-routing-suite | LLM 基础设施 | +2,149 | 7,031 |
| 16 — | hoainho/img2threejs | 多模态 | +2,051 | 4,176 |
| 17 — | Edge0-AI/Edge0 | LLM 基础设施 | +1,930 | 1,627 |
| 18 — | DietrichGebert/ponytail | Agent 智能体 | +1,869 | 100,293 |
| 19 — | Jarvis322/macos-sysdata | 工程化 | +1,841 | 564 |
| 20 — | anthropics/skills | Agent 智能体 | +1,722 | 167,649 |