A curated hub of autonomous-research skills & agents — from idea to paper, on autopilot. | 自主科研技能与智能体精选库 —— 从灵感到论文全文,全程自动完成。
- Stars
- 225
- Star gain
- +2
- Growth score
- 0.0089
Refreshing signal
Fetching the latest published ranking from Repovil.
AI open-source momentum index
Open-source signal / updated every 6 hours
Explore AI open-source repositories ranked by positive star growth over 24h. Compare recent momentum instead of lifetime popularity.
Browse AI Agents repositories grouped by the active GitHub topic mappings and ranked by recent star growth.
Live ranking
Published
A curated hub of autonomous-research skills & agents — from idea to paper, on autopilot. | 自主科研技能与智能体精选库 —— 从灵感到论文全文,全程自动完成。
Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.
Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.
雅思阅读与听力练习系统,支持题库浏览、套题练习、成绩记录、错题分析、数据备份与本地题库导入。
Pi Desktop: a free, open source desktop GUI for the Pi coding agent and oh-my-pi. Chat, edit files, run a terminal, and review diffs in one window. Linux, macOS, and Windows.
Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.
Community-maintained skills for specialized HyperFrames workflows.
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
Open-source (AGPL-3.0), self-hostable lights-out software factory for the agent era: label a GitHub Issue, get an independently reviewed, merged PR and a tagged release.
Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.
Vibe AStock:A 股短线复盘与跟踪工作台 · 盯盘异动、情绪复盘(连板天梯、题材轮动、明日验证)、AI 复盘与周报、交易日志、盘前提醒,182 个数据端点。支持 Claude Code、Codex、WorkBuddy 订阅或任意模型 API。 | A short-term trading review and tracking workbench for China A-shares.
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned.
Agentic coding TypeScript boilerplate for Claude Code: sub-agent workflows with built-in quality checks and context engineering.
Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.
Personal Corp OS — управление личной компанией через AI-агентов: задачи вне головы, отделы вместо памяти, недельное ретро. Открытые скиллы для Claude Code и Codex
Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust
Bambu Lab AI (Bambu Studio AI): agent skill for 3D printing on Bambu Lab. Finds models on MakerWorld & Printables, generates or designs them in CAD, checks printability, hands them to Bambu Studio and reads printer/AMS status. For Claude Code, Codex, Cursor, Gemini CLI and any SKILL.md agent. Featured in 我的拓竹 Skill 大赏.
Phil is a self-improving trader: an AI agent that trades short-term prediction markets and rewrites his own strategy after every settled bet. Paper 24/7 in the cloud; small capped real stakes via Pearl Connect.
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.
Momentum Score compares the latest star count with a baseline for the selected window: ln((current stars + 1) / (baseline stars + 1)). Rankings include repositories with positive star gain.
Seven-day and thirty-day history may use estimates reconstructed from GitHub star creation history; estimated values are labeled. The twenty-four-hour ranking uses measured snapshots only.