GitHub repositories taking off in the last 7 days
Ranked by how many more stars each repo got in the last 7 days than its pace over the 7 days before would predict, lowest first. Star counts come from GitHub. Last updated 9 Nov 2026, 09:20 UTC.
?
- 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: 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.
- Suspected
- Repositories with at least 50 stars are left out as likely bought stars when they have no detected programming language and got those stars within a day of being created; or got them within 14 days while having no watchers, at most 1 fork, no detected language or under 1 KB of code other than HTML and CSS, and either 5 KB or less of files or an owner that is a personal account with at most 1 follower. Repositories with no detected language are also left out when, at any age, they have 5 KB or less of files and got at least 90% of their stars on a single day that ended more than a day ago; or have 5 KB or less of files and belong to a personal account with no followers that was created at most an hour before the repository. Any repository with at least 50 stars is also left out when, under 3 days old, it has no watchers and at least 5 forks and belongs to a personal account with no followers; it stays out while that account has no followers. See them.
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 16751 |
Hierarchical agent loops with recursive self-organization. |
789 | 0 | 0 | +9 | -2 | 0 | 0.0x, slowing | |
| 16752 |
自动化 SRC 漏洞挖掘系统:FOFA 资产测绘 + LLM 多 worker 自主挖掘/审核/情报沉淀。Powered By StanleyNull |
543 | 0 | +13 | +72 | -2 | 0 | 0.9x, slowing | |
| 16753 |
Bird frame for Raspberry Pi or your homelab - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. On an e-ink panel, a TV, or any screen. |
4,003 | 0 | +29 | +394 | -2 | 0 | 0.9x, slowing | |
| 16754 |
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console. |
641 | 0 | +1 | +13 | -2 | 8 | 0.3x, slowing | |
| 16755 |
sanoTTS (सानो = 'small' in Nepali): a ~294k-1.4m param neural TTS that runs on a $3 chip or in the browser. Leads SCOREQ/UTMOS in the sub-15M class. |
836 | 0 | +10 | +55 | -2 | 0 | 0.8x, slowing | |
| 16756 |
你这只吃白饭的蓝色大肥鱼.jpg |
98 | 0 | +12 | +58 | -2 | 8 | 0.9x, slowing | |
| 16757 |
HugAgentOS: the open-source Agent Harness that runs 24/7 |
628 | 0 | +1 | +23 | -2 | 0 | 0.4x, slowing | |
| 16758 |
Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start coding right away. |
905 | 0 | +20 | +405 | -2 | 0 | 0.9x, slowing | |
| 16759 |
This project simulates cassette tape audio profiles using ffmpeg |
520 | 0 | +1 | +5 | -2 | 0 | 0.4x, slowing | |
| 16760 |
AgentENV (AENV) is a distributed platform for running agent environments at scale. |
3,732 | 0 | +14 | +124 | -2 | 0 | 0.9x, slowing | |
| 16761 |
Open-source Grok App — desktop workbench (GUI) for the local Grok Build CLI: sessions, projects, media, automations. Tauri 2. |
1,519 | 0 | +6 | +94 | -2 | 0 | 0.8x, slowing | |
| 16762 |
与 kejilion.sh 双向互通的开源 Linux 运维面板,支持双模式工作台、多主机管理与 AI 助手。 |
512 | 0 | +13 | +73 | -2 | 0 | 0.9x, slowing | |
| 16763 |
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone. |
667 | 0 | +1 | +13 | -2 | 0 | 0.4x, slowing | |
| 16764 |
DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达:持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照;插件目录为自动生成的产物 |
1,496 | 0 | +4 | +42 | -2 | 0 | 0.7x, slowing | |
| 16765 |
semantic agent kernel which make agent efficient and self-evolve |
811 | 0 | -1 | +4 | -2 | 0 | -1.2x, slowing | |
| 16766 |
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic. |
1,332 | 0 | +31 | +174 | -2 | 15 | 0.9x, slowing | |
| 16767 |
Official implementation of EVOKE: Endless Interactive World with Bounded State and Long-Horizon Supervision. A three-step, CFG-free interactive world model. SOTA on WBench. |
912 | 0 | +33 | +85 | -2 | 0 | 0.9x, slowing | |
| 16768 |
Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys |
574 | 0 | +26 | +132 | -2 | 0 | 0.9x, slowing | |
| 16769 |
All your AI agent sessions in one place — browse, search, resume. Rust + GPUI. |
1,548 | 0 | +26 | +118 | -2 | 0 | 0.9x, slowing | |
| 16770 |
no more refusals, do everything. |
301 | 0 | +28 | +300 | -2 | 44 | 0.9x, slowing | |
| 16771 |
DeepSeek 自带破甲 18+ 互动叙事:活人感 NPC(自主决策/拒绝迎合)、211个世界与上万素材、开局随心定制、世界自行运转、零漂移存档。 |
537 | 0 | +69 | +385 | -2 | 25 | 1.0x, steady | |
| 16772 |
Code for "Meta^n: Recursive Self-Improvement through Emergent Depth" |
86 | 0 | +3 | +51 | -2 | 0 | 0.6x, slowing | |
| 16773 |
recipe for running Qwen3.8-Flash-Next on a single DGX Spark |
511 | 0 | +14 | +89 | -2 | 8 | 0.9x, slowing | |
| 16774 |
Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow simulation and explicitly authorized broker execution. |
1,076 | 0 | 0 | +5 | -2 | 0 | 0.0x, slowing | |
| 16775 |
GLM-5.3 Flash EXL3 for 2-4x DGX Sparks |
754 | 0 | +5 | +43 | -2 | 8 | 0.7x, slowing | |
| 16776 |
SABER enables identity-resolved quantification of multi-animal social behavior |
222 | 0 | -3 | +214 | -2 | 0 | No data | |
| 16777 |
Template workspace for collaborative data analysis with Claude Code |
90 | 0 | +1 | +89 | -2 | 0 | 0.3x, slowing | |
| 16778 |
An inference engine for one NVIDIA RTX card, built for a coding agent and its subagents, and a companion that listens, reads and draws: Qwen3.8 27B and 125B Flash-Next MoE, Qwen-Image-2.1, Qwen3-ASR on the CPU. OpenAI-compatible API and Playground in one binary. |
61 | 0 | +11 | +50 | -2 | 0 | 0.8x, slowing | |
| 16779 |
Open Duet card feed: agents finish work, Magnus decides with one click |
507 | 0 | +3 | +100 | -2 | 0 | 0.6x, slowing | |
| 16780 |
No description |
621 | 0 | +3 | +354 | -2 | 0 | 0.6x, slowing | |
| 16781 |
Open Source Inertial Navigation Library |
669 | 0 | +8 | +53 | -2 | 0 | 0.8x, slowing | |
| 16782 |
backend, web frontend, etc. |
1,406 | 0 | +40 | +753 | -2 | 5 | 0.9x, slowing | |
| 16783 |
WorkBuddy 国际国内多账号反代网关,支持 Codex / Claude Code / DSH与标准 OpenAI 客户端。 |
3,760 | +4 | +328 | +2,838 | -2 | 245 | 1.0x, steady | |
| 16784 |
Qwen's most powerful open-source image generation model |
2,184 | 0 | +48 | +332 | -2 | 14 | 1.0x, steady | |
| 16785 |
Static recompilation of a PSP game into a native executable. Vulkan and SDL3. Bring your own copy of the game. |
598 | 0 | +30 | +208 | -2 | 6 | 0.9x, slowing | |
| 16786 |
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU. |
678 | 0 | +95 | +644 | -2 | 29 | 1.0x, steady | |
| 16787 |
Open-source code for training and scaling up energy-based foundation models. |
302 | +1 | +59 | +295 | -2 | 31 | 1.0x, steady | |
| 16788 |
mu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi. |
586 | 0 | +14 | +99 | -2 | 8 | 0.9x, slowing | |
| 16789 |
Coastal town built with Opus 5.5 |
1,447 | 0 | +25 | +240 | -2 | 7 | 0.9x, slowing | |
| 16790 |
No description |
761 | 0 | +6 | +59 | -2 | 0 | 0.8x, slowing | |
| 16791 |
A curated list of steam frame compatible software/hardware |
285 | 0 | +40 | +214 | -2 | 4 | 0.9x, slowing | |
| 16792 |
Isometric line figures that answer the pointer. For React and for anything with a DOM. |
3,541 | 0 | +228 | +1,918 | -2 | 31 | 1.0x, steady | |
| 16793 |
Desktop app for game dev with AI: make games in Unreal Engine, Unity, Godot or the browser. The agent sets up the engine, builds your game and play-tests it by itself. |
811 | 0 | +26 | +308 | -2 | 0 | 0.9x, slowing | |
| 16794 |
No description |
101 | 0 | -2 | +83 | -2 | 0 | No data | |
| 16795 |
Bloodborne running natively on Linux and the Steam Deck, built on bbport: online play and Seamless Co-op, unlocked FPS, ultrawide, FSR and DLSS, any controller, trophies, Add to Steam and a self-updating AppImage. Requires your own legally dumped copy of the game. |
147 | 0 | +19 | +146 | -2 | 0 | 0.9x, slowing | |
| 16796 |
Evidence-aware Japanese speech visualization: pitch and intonation, waveform inspection, and experimental alignment. |
175 | 0 | -3 | +171 | -2 | 0 | No data | |
| 16797 |
A free desktop encyclopedia for Windows, Mac, and Linux, inspired by the CD-ROM reference software of the early 2000s and powered by Wikipedia, online or offline. Public beta. |
54 | 0 | +8 | +54 | -2 | 8 | 0.8x, slowing | |
| 16798 |
麦茶团长 —— 团队下午茶拼单:链接化点单 + 实时满减看板 + 一键下单。基于麦当劳中国 MCP + WorkBuddy Skill(1024 程序员节参赛作品) |
107 | 0 | -2 | +104 | -2 | 0 | No data | |
| 16799 |
麦麦瘦身助手 · mcd-fit-buddy |
105 | 0 | -2 | +103all | -2 | 0 | No data | |
| 16800 |
A Japanese font that shows furigana by itself. |
430 | 0 | +7 | +430all | -2 | 0 | 0.8x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.