Fastest star growth over 8 hours
50–1,999 stars · gains since the previous 8-hour cycle · updated every 8 hours · Methodology
8-hour gain ranking · 1,153 projects
8h + shows stars gained since the previous cycle · ★ shows total stars
Cycle Nov 14, 08:00 KST · next scheduled Nov 14, 16:00 KST
- Rank 1
The coding-agent plugin that bills 52% of a bare model across 20 live tasks. Terse persona + tool-output compressor + context diet.
8h +111★ 913 - Rank 2
Real creator library videos at $11 and images at $8. Custom production from $25/video with a $250 minimum. Commercial licensing included.
8h +100★ 439 - Rank 3
Wenlan is a source-backed AI knowledge base and LLM wiki for AI work: organize documents and decisions into pages you can find, inspect, and review.
8h +38★ 167 - Rank 4
Give Claude Code, Codex, or Cursor a durable punch list, safety rules, recovery, and a reviewable morning handoff.
Translation pending
8h +36★ 427 - Rank 58h +28★ 185
- Rank 6
Argus 是开源的 Windows 任务管理器：原生 GPU 绘制界面，曲线随刷新率流动，可查端口、文件占用、每进程磁盘读写、磁盘健康和最近 7 天的历史。
Translation pending
8h +27★ 1,531 - Rank 7
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Translation pending
8h +26★ 1,188 - Rank 8
One OpenAI-compatible AI gateway for production AI — adaptive routing, load balancing, guardrails, agent firewall, observability and governance across 200+ models.
8h +21★ 660 - Rank 9
Automate with computer-use agent (ComputerUse / CUA) for macOS, Windows, Linux, Browser, iOS & Android. It sees the screen, clicks, types, browses and writes the code too. One agent, every computer.
8h +18★ 1,207 - Rank 10
Free, open-source touch screens. Guided USB setup, a drag-and-drop editor and local control. Made for Home Assistant.
8h +17★ 1,145 - Rank 11
☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
8h +17★ 690 - Rank 12
Full Linux VM sandboxes with hardware-level isolation. Long-running, checkpoint and fork, resize at runtime.
8h +17★ 608 - Rank 13
Without training models, RoboHarness combines visual clicks, keypoint tracking, and geometric constraints to provide an embodied control panel for an LLM agent.
8h +17★ 506 - Rank 14
An AI agent for your desktop and terminal, on any model you choose. Hosted models run on Fuel, paid in $DULUS.
8h +16★ 641 - Rank 15
A shared workspace for your team, Claude Code, and Codex. Bring your subscriptions, share tools and memory, and continue sessions across local, remote, and cloud runtimes.
8h +15★ 548
