Repositories taking off
?
- Stars gained
- New stars in the window. "all" means the repo is younger than the window, so the number is every star it has.
- Today
- Stars since midnight US Pacific time, so a partial day.
- Above pace
- How many more stars the repo got than its pace in the window before would predict. +500 means 500 more than usual.
- Momentum
- A daily score modeled on trendshift.io: 8 points per star and 2 per fork since midnight UTC, reduced for repos that are this busy every day.
- Speed-up
- Stars per day in the window divided by stars per day in the window before. "New" means the repo is younger than the window. "Under 14 days" (twice the window; "Under 2 years" for 1 year) means it is older than the window but too young for a full window before it to compare with.
- Bars
- Stars per day (per week for 90 days and 1 year). Bright bars are the selected window. Heights use a square-root scale, so quieter days stay visible next to a spike.
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 4101 |
Open-source Grok Bot alternative. Choose your own model and sandbox. |
6,043 | +80 | +1,071 | +3,057 | -2 | 584 | 1.0x, steady | |
| 4102 |
Advanced NVIDIA GPU tuning and monitoring for Windows. Control voltage, clocks, power and cooling with V/F curves, fan curves, live telemetry, saved profiles and software BIOS override. |
557 | +3 | +47 | +147 | -2 | 23 | 0.6x, slowing | |
| 4103 |
A local desktop app that turns videos and images into 3D Gaussian Splats in one click. |
2,142 | +8 | +76 | +529 | -2 | 134 | 0.8x, slowing | |
| 4104 |
PosterBoard Wallpapers for iOS 26 - 27 |
608 | +3 | +37 | +168 | -2 | 48 | 0.6x, slowing | |
| 4105 |
🖥️ Agent-project workbench for DeepSeek Harness — sidebar app drawer + dockable split workspace + a live control room watching every project. |
802 | +1 | +32 | +130 | -2 | 6 | 0.3x, slowing | |
| 4106 |
Zetta is an efficient closed-loop embodied harness for self-evolving physical intelligence. It evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Project Page: https://air-embodied-brain.github.io/zetta/ |
1,307 | 0 | +10 | +50 | -2 | 8 | 0.0x, slowing | |
| 4107 |
Watch a Claude Code or Codex session as a live flow graph, in your terminal or your browser. |
1,113 | +2 | +46 | +165 | -2 | 50 | 0.5x, slowing | |
| 4108 |
AI Chat with powerful models for free |
1,514 | 0 | +7 | +140 | -2 | 0 | 0.0x, slowing | |
| 4109 |
《深入理解 AI Infra:量化分析与系统设计》(李博杰 著)开源书稿:从硬件约束和模型架构出发,量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验 |
7,054 | +24 | +248 | +1,646 | -2 | 330 | 0.9x, slowing | |
| 4110 |
A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse. |
875 | +2 | +57 | +281 | -2 | 30 | 0.6x, slowing | |
| 4111 |
AI 时代的私人影库 |
1,118 | +8 | +145 | +535 | -2 | 83 | 0.8x, slowing | |
| 4112 |
Codex skill for building responsive 3D photo flipbook websites from user-supplied images |
604 | +15 | +57 | +190 | -2 | 254 | 0.9x, slowing | |
| 4113 |
you're telling me a shrimp made this video?! |
1,218 | 0 | +6 | +70 | -2 | 0 | 0.0x, slowing | |
| 4114 |
Compass: run your whole life out of Obsidian. Daily questions, quarterly retreats, planning, habits, tasks, writing, and an AI assistant in the vault. |
1,024 | +2 | +27 | +169 | -2 | 16 | 0.6x, slowing | |
| 4115 |
Cross-Platform Micro-VM Sandbox for Agentic Workloads |
784 | +7 | +232 | +775 | -2 | 79 | 0.8x, slowing | |
| 4116 |
The best file manager on Linux |
1,479 | +13 | +96 | +948 | -2 | 176 | 0.9x, slowing | |
| 4117 |
Infrastructure for continually self‑improving agents |
7,755 | +8 | +49 | +1,174 | -2 | 106 | 0.8x, slowing | |
| 4118 |
cn is a new engine for Tailwind class merging and conflict resolution. It replaces tailwind-merge and clsx. Same APIs. Full parity. And it is 30× faster. |
1,716 | 0 | +17 | +123 | -2 | 8 | 0.0x, slowing | |
| 4119 |
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi. |
739 | +3 | +44 | +204 | -2 | 40 | 0.6x, slowing | |
| 4120 |
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents. |
616 | 0 | +13 | +158 | -2 | 8 | 0.0x, slowing | |
| 4121 |
AIにまじなPPTXを作らせる Claude Code / Codex スキル |
1,436 | +1 | +29 | +623 | -2 | 34 | 0.3x, slowing | |
| 4122 |
Open source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the files. |
806 | +6 | +141 | +349 | -2 | 49 | 0.8x, slowing | |
| 4123 |
Orbit is a native desktop workbench for the pi coding agent — a chat-style GUI rendered entirely in Rust on GPUI, the GPU-accelerated UI framework Zed is built on. It speaks the pi CLI's RPC protocol directly over stdio: no browser, no webview, no Node. |
130 | 0 | +82 | +101 | -2 | 4 | 0.0x, slowing | |
| 4124 |
真实 API 定价:订阅月费 ÷ 实际可用 token,含额度、单价与分榜帕累托图。Real API pricing: subscription fee ÷ usable tokens, with allowance, unit-price, and leaderboard Pareto charts. |
1,011 | +2 | +52 | +410 | -2 | 40 | 0.6x, slowing | |
| 4125 |
V2rayN,Clash系列,Karing等主流代理软件的完美分流规则源文件,下载直接使用。 |
1,451 | +9 | +83 | +553 | -2 | 96 | 0.8x, slowing | |
| 4126 |
Open Source Inertial Navigation Library |
650 | 0 | +16 | +79 | -2 | 0 | 0.0x, slowing | |
| 4127 |
AI Bro — a local-first workspace for AI conversations, source-linked knowledge, and tasks. |
786 | +10 | +114 | +415 | -2 | 120 | 0.8x, slowing | |
| 4128 |
A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory. |
573 | 0 | +27 | +138 | -2 | 0 | 0.0x, slowing | |
| 4129 |
KVMem virtualizes KV memory across inference backends to make ultra-long-context local AI accessible on limited hardware. |
1,171 | +3 | +58 | +488 | -2 | 31 | 0.6x, slowing | |
| 4130 |
A macOS menu-bar app that dresses your windows in knitted borders. |
823 | +1 | +19 | +110 | -2 | 8 | 0.3x, slowing | |
| 4131 |
A Multilingual, Multimodal Translation Model Family |
1,812 | +14 | +121 | +1,809 | -2 | 196 | 0.9x, slowing | |
| 4132 |
Receive-only Wi-Fi and Bluetooth LE observer for Android. MIT. |
4,168 | +11 | +194 | +4,039 | -2 | 115 | 0.8x, slowing | |
| 4133 |
The best agent harness. |
297 | +16 | +238 | +277 | -2 | 218 | 0.9x, slowing | |
| 4134 |
No description |
250 | +2 | +52 | +207 | -2 | 50 | 0.6x, slowing | |
| 4135 |
One AI trade decision every Monad block. Jev on Kuru MON-USDC. |
3,094 | +2 | +47 | +510 | -2 | 32 | 0.6x, slowing | |
| 4136 |
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers. |
667 | 0 | +14 | +158 | -2 | 10 | 0.0x, slowing | |
| 4137 |
Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud. |
1,040 | +4 | +92 | +848 | -2 | 41 | 0.7x, slowing | |
| 4138 |
Rules, playbooks, bot roles and a failure log from the xAI Grok Bot team's 72-hour live build. Drop AGENTS.md into your repo and go. |
638 | -1 | +29 | +91 | -2 | 0 | -0.8x, slowing | |
| 4139 |
Make your coding agent abide by all your project rules |
612 | 0 | +22 | +245 | -2 | 8 | 0.0x, slowing | |
| 4140 |
DSH 朗读桥:会话里的话自动交给 DeepSeek 网页端朗读,声音从你自己的电脑里出来 |
158 | +14 | +148 | +153 | -2 | 170 | 0.9x, slowing | |
| 4141 |
DLSS 5 Neural Rendering on AMD GPUs, built into OptiScaler: model interleave, residual composition, XeSS frame generation up to 6X, FSR Ray Regeneration. Discord: https://discord.gg/AMDNR · Ko-fi: https://ko-fi.com/3zinr |
724 | +2 | +65 | +619 | -2 | 38 | 0.5x, slowing | |
| 4142 |
Open Source virtual tabletop for Obsidian: battle maps, tokens, fog of war, dice, initiative and a separate player view. |
638 | 0 | +16 | +612 | -2 | 8 | 0.0x, slowing | |
| 4143 |
Open, lightweight multimodal decision models for text, images, and video. Train and run them yourself. |
885 | 0 | +17 | +580 | -2 | 26 | 0.0x, slowing | |
| 4144 |
Agent skills and design systems from design.how. Build a design system from your app, use agents to ship UI, enforce it in CI. |
202 | +2 | +58 | +202 | -2 | 31 | 0.6x, slowing | |
| 4145 |
明日方舟「卫戍协议:盟约」非官方同人复刻:浏览器自走棋塔防,单人或 1–4 人联机合作(非商业) |
1,777 | +2 | +95 | +1,776all | -2 | 14 | 0.5x, slowing | |
| 4146 |
AI API 中转站评测排行与切换工具:实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex |
3,790 | +36 | +1,589 | +3,663all | -2 | 137 | 1.0x, steady | |
| 4147 |
ScopeWeaver: English and Korean localization of ARTEX, with preserved AGPL-3.0 attribution. |
817 | +15 | +85 | +816all | -2 | 176 | 0.9x, slowing | |
| 4148 |
Code-first video & image, rendered natively on WebGPU. |
492 | 0 | +37 | +492all | -2 | 0 | 0.0x, slowing | |
| 4149 |
Build voice and text devices for your Hermes Agent, with ESP32 firmware, a Linux client, and a desktop simulator. |
448 | +1 | +25 | +448all | -2 | 24 | 0.3x, slowing | |
| 4150 |
An unofficial original Xbox version PC port of BLACK (2006) via static recompilation. |
779 | +7 | +176 | +777all | -2 | 62 | 0.8x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 134 more tracked repositories are still loading their star history and will join the ranking once it is complete.