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 40 min ago
Columns
| # | Repository | Stars | Today | 7d | 30d | Above pace ↑ | Momentum | Speed-up | Daily stars |
|---|---|---|---|---|---|---|---|---|---|
| 551 |
A modern and faithful open source rebuild of the Tiberian Sun engine. |
593 | +1 | +8 | +52 | -352 | 18 | 0.1x, slowing | |
| 552 |
🔬 Harness Vibe Research with Self-evolving AI Scientists |
4,917 | 0 | +14 | +83 | -351 | 0 | 0.2x, slowing | |
| 553 |
Modular SenseNova skills for building AI-powered office assistants and productivity workflows |
5,927 | +7 | +140 | +248 | -350 | 77 | 0.4x, slowing | |
| 554 |
A powerful, all-in-one Discord assistant built for every server. |
9,204 | +10 | +161 | +898 | -346 | 93 | 0.7x, slowing | |
| 555 |
A next generation HTTP client for Python. 🦋 |
1,588 | +3 | +30 | +101 | -346 | 42 | 0.2x, slowing | |
| 556 |
Bootstrap Kubernetes the hard way. No scripts. |
50,473 | +7 | +54 | +319 | -345 | 64 | 0.5x, slowing | |
| 557 |
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention |
15,098 | +20 | +448 | +1,482 | -345 | 188 | 0.8x, slowing | |
| 558 |
1,324-exercise fitness dataset — animation GIFs, 180×180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app. |
23,238 | +18 | +178 | +981 | -344 | 170 | 0.7x, slowing | |
| 559 |
Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows |
13,541 | +44 | +361 | +1,884 | -344 | 484 | 0.8x, slowing | |
| 560 |
An open-source, macOS text action popup for running custom scripts, AI actions, and extensible workflows on selected text. |
712 | +1 | +18 | +175 | -344 | 18 | 0.3x, slowing | |
| 561 |
可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. |
7,504 | +6 | +72 | +309 | -343 | 118 | 0.5x, slowing | |
| 562 |
OpenWiki is a CLI that writes and maintains agent documentation for your codebase. |
17,458 | +14 | +179 | +717 | -342 | 412 | 0.7x, slowing | |
| 563 |
Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes. |
6,437 | +9 | +67 | +451 | -341 | 120 | 0.6x, slowing | |
| 564 |
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks. |
2,244 | +12 | +124 | +544 | -341 | 91 | 0.6x, slowing | |
| 565 |
A community-supported supercharged document management system: scan, index and archive all your documents |
47,108 | +6 | +237 | +1,112 | -338 | 58 | 0.8x, slowing | |
| 566 |
Bento, the office suite that fits in a file |
5,566 | +1 | +46 | +352 | -338 | 24 | 0.5x, slowing | |
| 567 |
:house_with_garden: Open source home automation that puts local control and privacy first. |
91,739 | +8 | +165 | +749 | -337 | 89 | 0.7x, slowing | |
| 568 |
Browse media content with your own rules on Android TV |
35,572 | +24 | +395 | +1,480 | -337 | 207 | 0.8x, slowing | |
| 569 |
Know how much Claude Code, Codex, Cursor, Copilot and 70+ other AI coding tools you have left — a free, open-source macOS monitor on the edge of your screen. |
599 | +2 | +22 | +126 | -337 | 26 | Under 60 days | |
| 570 |
The ESP32-BlueJammer (Bluetooth jammer, BLE jammer, WiFi jammer, RC jammer) disrupts 2.4GHz communications. Using an ESP32 and nRF24 modules, it generates noise and unnecessary packets, causing interference between the devices communicating, making them unable to work as intended. Ideal for controlled disruption and security testing. |
8,731 | +6 | +50 | +295 | -336 | 74 | 0.5x, slowing | |
| 571 |
Summer 2027 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC. |
48,163 | +21 | +143 | +616 | -335 | 300 | 0.6x, slowing | |
| 572 |
CubePlex is a cloud-native platform for managed agents in team workspaces — skills, shared memory, MCP tools, persistent sandboxes, governed access, and self-hosted deploy on Docker Compose or Kubernetes. |
561 | +3 | +21 | +105 | -335 | 32 | 0.2x, slowing | |
| 573 |
TradingAgents: Multi-Agents LLM Financial Trading Framework |
115,593 | +642 | +3,481 | +7,188 | -333 | 6,328 | 1.0x, steady | |
| 574 |
Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark. |
705 | 0 | +14 | +98 | -332 | 10 | 0.2x, slowing | |
| 575 |
Open-source auth gateway connecting 1500+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI. |
6,093 | +1 | +50 | +223 | -330 | 7 | 0.4x, slowing | |
| 576 |
BigBanana AI Director是一个工业级一站式 AI 短剧,AI 漫剧,AI 导演平台,面向创作者,实现从灵感到成片的高效生产。 它摇弃了传统的“抽卡式”生成,采用 "Script-to-Asset-to-Keyframe" 的工业化工作流。实现 “一句话生成完整短剧,从剧本到成片全自动化”,同时精准控制角色一致性、场景连续性与镜头运动。 |
2,377 | +1 | +26 | +161 | -329 | 0 | 0.3x, slowing | |
| 577 |
Autonomous game development with Claude Code and Codex |
7,217 | +3 | +50 | +241 | -329 | 58 | 0.4x, slowing | |
| 578 |
The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment. |
4,270 | +4 | +52 | +294 | -327 | 50 | 0.5x, slowing | |
| 579 |
Weather, tides, the sun, the moon, maps, and a planetarium, in your terminal. The Old Farmer's Almanac meets Minitel. |
646 | +3 | +12 | +96 | -327 | 32 | 0.2x, slowing | |
| 580 |
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training |
2,637 | 0 | +1 | +10 | -327 | 0 | 0.0x, slowing | |
| 581 |
The batteries-included agent harness. |
30,610 | +19 | +185 | +877 | -326 | 258 | 0.7x, slowing | |
| 582 |
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU |
1,037 | +30 | +285 | +349 | -326 | 510 | 0.5x, slowing | |
| 583 |
Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files. |
4,061 | +1 | +2 | +48 | -325 | 12 | 0.1x, slowing | |
| 584 |
ProxCenter is an alternative to VMware vCenter for Proxmox environments. It provides a modern, intuitive web interface to manage multiple Proxmox VE clusters and Proxmox Backup Server instances from a single pane of glass. |
1,741 | +1 | +14 | +68 | -325 | 8 | 0.2x, slowing | |
| 585 |
A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more. |
1,684 | +1 | +17 | +139 | -323 | 12 | 0.3x, slowing | |
| 586 |
美股指南 |
7,797 | +5 | +65 | +555 | -323 | 64 | 0.6x, slowing | |
| 587 |
把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills) |
11,767 | +29 | +281 | +1,190 | -321 | 315 | 0.8x, slowing | |
| 588 |
AI-guided editable scientific figures with Codex and local Origin/OriginPro |
1,010 | +4 | +43 | +238 | -321 | 56 | 0.4x, slowing | |
| 589 |
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. |
732 | +4 | +40 | +200 | -321 | 40 | Under 60 days | |
| 590 |
Skills for Design Engineers |
10,209 | +18 | +334 | +1,100 | -320 | 152 | 0.8x, slowing | |
| 591 |
Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust. |
3,324 | -1 | +4 | +49 | -320 | 0 | 0.1x, slowing | |
| 592 |
Just a VLM Agent Can Play Robots |
587 | +1 | +17 | +129 | -320 | 16 | Under 60 days | |
| 593 |
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent |
30,732 | +13 | +336 | +1,004 | -319 | 115 | 0.8x, slowing | |
| 594 |
CLI runbook for agent long run. |
1,493 | +2 | +66 | +277 | -318 | 39 | 0.5x, slowing | |
| 595 |
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. |
41,199 | 0 | +92 | +514 | -317 | 19 | 0.6x, slowing | |
| 596 |
Browser automation CLI for AI agents |
44,626 | +26 | +333 | +1,521 | -317 | 265 | 0.8x, slowing | |
| 597 |
基于 Rust 的低风控、高性能、自托管多账号透明代理网关 |
963 | +8 | +83 | +316 | -317 | 106 | 0.5x, slowing | |
| 598 |
Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent. |
700 | +1 | +26 | +132 | -317 | 16 | 0.3x, slowing | |
| 599 |
Give your AI a full stack: memory, voice, face, and hands. This is the "I want an AI agent" shortcut. It sets up the entire jaredrhod stack for you with an installation wizard. Select which pieces you want or do it all! |
1,171 | +2 | +45 | +208 | -317 | 18 | 0.4x, slowing | |
| 600 |
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard. |
4,634 | +1 | +17 | +90 | -316 | 10 | 0.2x, slowing |
Today counts stars since midnight US Pacific time, so it is a partial day.