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.
Updated 33 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 451 |
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. |
50,723 | +22 | +462 | +1,950 | -451 | 280 | 0.8x, slowing | |
| 452 |
A Terminal-style trading dashboard built entirely on free public market data. No API keys, no subscriptions. |
2,044 | +4 | +173 | +781 | -451 | 65 | 0.6x, slowing | |
| 453 |
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. |
208,638 | +23 | +640 | +3,322 | -448 | 219 | 0.9x, slowing | |
| 454 |
Open-Sora: Democratizing Efficient Video Production for All |
29,877 | -1 | +16 | +92 | -448 | 8 | 0.2x, slowing | |
| 455 |
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it. |
3,245 | +10 | +106 | +710 | -444 | 114 | 0.6x, slowing | |
| 456 |
The Modular Platform (includes MAX & Mojo) |
30,046 | +2 | +76 | +220 | -442 | 56 | 0.3x, slowing | |
| 457 |
CLI tool for configuring and monitoring Claude Code |
32,914 | +11 | +176 | +1,111 | -442 | 148 | 0.7x, slowing | |
| 458 |
Experimental next generation frontend tooling. |
613 | 0 | +5 | +49 | -442 | 0 | 0.1x, slowing | |
| 459 |
Split any YouTube song into stems |
1,131 | 0 | +51 | +337 | -439 | 0 | 0.4x, slowing | |
| 460 |
Personal AI Toolbox |
1,786 | +1 | +6 | +58 | -437 | 8 | 0.1x, slowing | |
| 461 |
LLM inference in C/C++ |
132,417 | +36 | +718 | +3,317 | -435 | 338 | 0.9x, slowing | |
| 462 |
AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation |
6,955 | +7 | +85 | +336 | -435 | 100 | 0.4x, slowing | |
| 463 |
A living space where people and agents create, play, and build together. |
575 | 0 | +4 | +10 | -434 | 0 | 0.0x, slowing | |
| 464 |
Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex. |
791 | +2 | +34 | +149 | -434 | 24 | 0.3x, slowing | |
| 465 |
Cross-platform Cloudflare Turnstile solver (macOS, Windows, Linux) |
509 | 0 | +8 | +32 | -433 | 0 | Under 60 days | |
| 466 |
WinUI: a modern UI framework with a rich set of controls and styles to build dynamic and high-performing Windows applications. |
8,557 | +1 | +18 | +107 | -432 | 24 | 0.2x, slowing | |
| 467 |
Mario Kart Wii and Retro Rewind, native for iOS, iPadOS, macOS, tvOS, and Android. |
715 | 0 | +28 | +136 | -430 | 6 | 0.2x, slowing | |
| 468 |
Evenfire is an intelligence layer platform for running LLM agents that take real actions, on your infrastructure |
568 | 0 | 0 | +32 | -428 | 0 | 0.1x, slowing | |
| 469 |
AI coworker with memory and collaboration |
18,087 | +1 | +52 | +158 | -427 | 15 | 0.3x, slowing | |
| 470 |
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 | +31 | +100 | -426 | 24 | Under 60 days | |
| 471 |
PocketJS: create UI on every screen you love. JavaScript components drawn as native pixels on handhelds, desktops and embedded screens. Also home to Pocket3D and MicroTS. |
1,801 | +1 | +35 | +151 | -425 | 14 | 0.3x, slowing | |
| 472 |
The Privacy First PDF Toolkit |
16,151 | +5 | +61 | +461 | -421 | 66 | 0.5x, slowing | |
| 473 |
Create, adapt, schedule, and track social posts. Open-source, hosted or self-hosted. |
778 | +7 | +31 | +158 | -420 | 114 | 0.3x, slowing | |
| 474 |
"AI-Trader: 100% Fully-Automated Agent-Native Trading" |
22,963 | +3 | +102 | +484 | -419 | 54 | 0.5x, slowing | |
| 475 |
天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同时对deepseek v4极度优化。 |
1,156 | +2 | +19 | +229 | -419 | 24 | 0.4x, slowing | |
| 476 |
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern. |
15,841 | +15 | +199 | +685 | -417 | 177 | 0.6x, slowing | |
| 477 |
A lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs in the web browser, on the desktop, on mobile, and inside Jupyter notebooks. |
8,139 | +7 | +92 | +476 | -413 | 112 | 0.5x, slowing | |
| 478 |
Self-hosted realtime soundscape analyser for birds, bats and other wildlife. Multi-model local AI inference, runs 24/7 on a Raspberry Pi. |
2,363 | +3 | +49 | +176 | -409 | 32 | 0.3x, slowing | |
| 479 |
In-depth tutorials on LLMs, RAGs and real-world AI agent applications. |
38,441 | +5 | +75 | +472 | -409 | 110 | 0.5x, slowing | |
| 480 |
Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys. |
2,173 | +1 | +42 | +153 | -409 | 6 | 0.3x, slowing | |
| 481 |
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability. |
24,139 | +5 | +79 | +423 | -408 | 59 | 0.5x, slowing | |
| 482 |
Virtual whiteboard for sketching hand-drawn like diagrams |
134,588 | +29 | +402 | +1,915 | -407 | 261 | 0.8x, slowing | |
| 483 |
AI-powered bug bounty hunting toolkit that works with or without subscription. |
5,444 | +7 | +76 | +305 | -406 | 88 | 0.4x, slowing | |
| 484 |
Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention |
2,729 | +4 | +147 | +449 | -406 | 34 | 0.5x, slowing | |
| 485 |
A good looking terminal emulator which mimics the old cathode display... |
26,533 | -1 | +16 | +112 | -402 | 0 | 0.2x, slowing | |
| 486 |
Wiicompiled |
1,278 | +2 | +76 | +285 | -402 | 36 | 0.4x, slowing | |
| 487 |
Langflow is a powerful tool for building and deploying AI-powered agents and workflows. |
156,030 | +6 | +237 | +1,177 | -399 | 54 | 0.7x, slowing | |
| 488 |
Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync |
700 | +3 | +11 | +144 | -399 | 24 | Under 60 days | |
| 489 |
GTM agent for technical founders. Pay-per-result. Two surfaces: terminal CLI + local web dashboard. |
671 | +1 | -2 | +1 | -398 | 8 | 0.0x, slowing | |
| 490 |
claude-opus-5-5-demo |
1,184 | -1 | +49 | +383 | -398 | 40 | Under 60 days | |
| 491 |
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git. |
521 | 0 | +1 | +36 | -397 | 0 | 0.1x, slowing | |
| 492 |
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. |
37,834 | +2 | +90 | +409 | -395 | 50 | 0.5x, slowing | |
| 493 |
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines. |
11,431 | +3 | +25 | +147 | -395 | 40 | 0.3x, slowing | |
| 494 |
Mimir — 一站式科研工作台插件：LaTeX 论文边写边编译、arXiv 文献管理、实验追踪、指标图表、GPU 服务器 SSH 任务编排，管理科研全周期。An open-source research workbench plugin for the whole research cycle. |
547 | 0 | +6 | +26 | -395 | 0 | 0.1x, slowing | |
| 495 |
git push no-mistakes |
8,974 | +9 | +82 | +379 | -394 | 136 | 0.5x, slowing | |
| 496 |
Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT. |
18,630 | +10 | +137 | +569 | -393 | 150 | 0.6x, slowing | |
| 497 |
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP. |
4,785 | +4 | +102 | +410 | -392 | 67 | 0.5x, slowing | |
| 498 |
Bypass llm guardrails by confusing it with fabricated tool output. |
589 | 0 | +57 | +93 | -392 | 0 | 0.2x, slowing | |
| 499 |
Unlock DLSS Upscaler, Multi-Frame Generation (MFG) and DLSS Neural Rendering features on any NVIDIA RTX GPU in any DirectX 12 game that supports DLSS2 and DLSS3 natively. |
903 | +4 | +46 | +248 | -392 | 32 | Under 60 days | |
| 500 |
An offline-first photo manager for large local libraries |
4,078 | +6 | +113 | +827 | -390 | 45 | 0.7x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.