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 20 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | 90d | Above pace ↑ | Momentum | Speed-up | Weekly stars |
|---|---|---|---|---|---|---|---|---|---|---|
| 351 |
Postgres rewritten in Rust, now faster than Postgres and Clickhouse |
5,518 | +13 | +242 | +387 | +1,687 | -2,082 | 203 | 0.4x, slowing | |
| 352 |
Use Claude Code, Codex, Antigravity, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly) |
63,602 | +60 | +1,702 | +8,140 | +21,738 | -2,075 | 568 | 0.9x, slowing | |
| 353 |
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. |
176,620 | +241 | +8,420 | +31,025 | +86,847 | -2,071 | 995 | Under 180 days | |
| 354 |
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. |
60,117 | +8 | +243 | +1,181 | +4,152 | -2,055 | 135 | 0.7x, slowing | |
| 355 |
An evolving how-to guide for securing a Linux server. |
31,845 | +2 | +31 | +430 | +2,007 | -2,052 | 32 | 0.5x, slowing | |
| 356 |
Free and open source database client built natively for developers |
6,320 | -1 | +44 | +381 | +1,034 | -2,031 | 6 | 0.3x, slowing | |
| 357 |
The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable. |
23,771 | +1 | +55 | +272 | +939 | -2,023 | 40 | 0.3x, slowing | |
| 358 |
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex. |
3,828 | 0 | +35 | +205 | +889 | -2,021 | 0 | Under 180 days | |
| 359 |
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. |
208,628 | +13 | +630 | +3,312 | +11,876 | -1,993 | 160 | 0.9x, slowing | |
| 360 |
Pretty fancy and modern terminal file manager |
23,934 | +6 | +73 | +636 | +2,456 | -1,989 | 48 | 0.6x, slowing | |
| 361 |
Redefining the open-source download manager |
11,230 | +5 | +129 | +811 | +2,390 | -1,968 | 84 | 0.5x, slowing | |
| 362 |
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps |
49,361 | +4 | +200 | +949 | +3,503 | -1,966 | 89 | 0.6x, slowing | |
| 363 |
Your GitHub stats, turned into a World-Cup-style player card |
2,660 | +3 | +12 | +57 | +345 | -1,950 | 16 | Under 180 days | |
| 364 |
LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths. |
3,901 | 0 | +12 | +82 | +523 | -1,931 | 24 | 0.2x, slowing | |
| 365 |
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta. |
5,503 | 0 | +16 | +123 | +1,770 | -1,929 | 0 | 0.5x, slowing | |
| 366 |
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 50 other agents. |
6,275 | +2 | +72 | +321 | +1,736 | -1,921 | 22 | 0.5x, slowing | |
| 367 |
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/ |
57,207 | +38 | +1,828 | +6,722 | +11,337 | -1,915 | 279 | 0.9x, slowing | |
| 368 |
Terminal coding agent powered by Kimchi's multi-model orchestration |
2,277 | 0 | +4 | +57 | +174 | -1,909 | 8 | 0.1x, slowing | |
| 369 |
Orchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for. |
24,323 | +4 | +105 | +475 | +1,639 | -1,898 | 72 | 0.5x, slowing | |
| 370 |
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents. |
4,929 | +10 | +107 | +327 | +1,281 | -1,888 | 132 | 0.4x, slowing | |
| 371 |
No description |
7,565 | +2 | +46 | +193 | +956 | -1,886 | 13 | 0.3x, slowing | |
| 372 |
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems. |
4,777 | +6 | +61 | +333 | +1,433 | -1,879 | 66 | 0.4x, slowing | |
| 373 |
Context7 Platform -- Up-to-date docs for AI agents |
63,709 | +17 | +388 | +1,421 | +4,208 | -1,876 | 212 | 0.7x, slowing | |
| 374 |
基于Python的开源量化交易平台开发框架 |
46,075 | +13 | +137 | +604 | +2,298 | -1,875 | 164 | 0.6x, slowing | |
| 375 |
基于 OpenAI gpt-image-2.5 API 的图片生成与编辑工具 |
3,970 | +2 | +46 | +200 | +787 | -1,863 | 48 | 0.3x, slowing | |
| 376 |
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent. |
18,100 | +17 | +354 | +1,460 | +4,282 | -1,858 | 238 | 0.7x, slowing | |
| 377 |
A fully-featured team and group chat application that you can easily selfhost. |
2,869 | 0 | +28 | +82 | +503 | -1,843 | 0 | 0.2x, slowing | |
| 378 |
Build resilient agents. |
43,924 | +20 | +385 | +1,692 | +5,771 | -1,841 | 239 | 0.8x, slowing | |
| 379 |
CodexGuide：面向全球初学者、创作者、开发者与团队的 Codex 实践指南 |
3,853 | +2 | +35 | +231 | +995 | -1,838 | 42 | Under 180 days | |
| 380 |
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor. |
8,598 | +3 | +81 | +282 | +893 | -1,836 | 45 | 0.3x, slowing | |
| 381 |
The headless browser for AI agents and web scraping |
29,399 | +10 | +351 | +1,544 | +9,852 | -1,825 | 128 | 0.8x, slowing | |
| 382 |
OpenTalking: An industrial-grade open-source AI digital human framework that supports real-time conversation, private deployment, and pluggable models. |
3,219 | 0 | +29 | +162 | +679 | -1,824 | 0 | 0.3x, slowing | |
| 383 |
Eagle: Frontier Vision-Language Models with Data-Centric Strategies |
3,726 | 0 | +15 | +115 | +474 | -1,822 | 0 | 0.2x, slowing | |
| 384 |
Open source, privacy-first web analytics. Lightweight, cookie-free Google Analytics alternative. Self-hosted or cloud. |
29,666 | +3 | +112 | +488 | +1,642 | -1,816 | 64 | 0.5x, slowing | |
| 385 |
Robust Speech Recognition via Large-Scale Weak Supervision |
111,292 | +18 | +427 | +1,877 | +5,803 | -1,810 | 186 | 0.8x, slowing | |
| 386 |
No description |
4,149 | 0 | +19 | +56 | +203 | -1,796 | 16 | 0.1x, slowing | |
| 387 |
Comfortably monitor your network traffic 🕵️♂️ |
41,699 | +1 | +79 | +544 | +1,701 | -1,795 | 32 | 0.5x, slowing | |
| 388 |
🩵 A free, open-source app store for developers' releases on GitHub, Codeberg & Forgejo — browse, discover, and install apps with one click. Formerly GitHub Store. |
19,896 | +14 | +277 | +1,199 | +3,072 | -1,780 | 175 | 0.6x, slowing | |
| 389 |
Receiving unencrypted data with MITM, Then send it with DomainFronting |
2,944 | 0 | +21 | +61 | +261 | -1,771 | 8 | 0.1x, slowing | |
| 390 |
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces |
11,292 | +3 | +36 | +175 | +852 | -1,768 | 40 | 0.3x, slowing | |
| 391 |
Breakthrough Method for Agile Ai Driven Development |
54,572 | +13 | +253 | +1,214 | +3,782 | -1,757 | 130 | 0.7x, slowing | |
| 392 |
Hysteria is powerful, lightning-fast, and censorship-resistant open-source proxy software |
22,737 | +2 | +57 | +228 | +721 | -1,753 | 32 | 0.3x, slowing | |
| 393 |
The simplest, fastest repository for training/finetuning medium-sized GPTs. |
64,084 | +5 | +165 | +794 | +2,719 | -1,753 | 33 | 0.6x, slowing | |
| 394 |
Comet: agent skill harness for turning ideas into evaluated workflows |
3,232 | 0 | +23 | +140 | +729 | -1,752 | 0 | Under 180 days | |
| 395 |
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。 |
3,108 | 0 | +9 | +82 | +245 | -1,751 | 0 | 0.1x, slowing | |
| 396 |
🗽Бесплатные и проверенные VPN/Tor конфигурации, работающие в РФ ⚪ Белые списки / обход белых списков ⚪ Free and checked VPN/Tor configurations that work in Russia ⚪ Whitelists bypass |
9,335 | +6 | +76 | +461 | +1,696 | -1,747 | 88 | 0.5x, slowing | |
| 397 |
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more. |
29,028 | +2 | +119 | +607 | +1,759 | -1,727 | 26 | 0.5x, slowing | |
| 398 |
AI-friendly PPT builder skill: 17 hand-polished Chinese PPTX templates + non-destructive text-only editing tools (python-pptx based). Pick a template, write edits.json, build a real .pptx with the layout intact. Personal/research use only. |
3,792 | +3 | +108 | +659 | +1,022 | -1,722 | 37 | Under 180 days | |
| 399 |
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training |
2,637 | 0 | +1 | +10 | +449 | -1,718 | 0 | 0.2x, slowing | |
| 400 |
Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案 |
6,189 | +3 | +37 | +182 | +1,150 | -1,715 | 60 | 0.4x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day. 597 more tracked repositories are still loading their star history and will join the ranking once it is complete.