Fastest star growth over 8 hours
50–1,999 stars · gains since the previous 8-hour cycle · updated every 8 hours · Methodology
8-hour gain ranking · 1,184 projects
8h + shows stars gained since the previous cycle · ★ shows total stars
Cycle Nov 6, 00:00 KST · next scheduled Nov 6, 08:00 KST
- Rank 61
Curated reverse-engineering tools and learning resources for binaries, apps, firmware, formats, and protocols.
8h +8★ 1,852 - Rank 628h +8★ 1,608
- Rank 63
A free AI assistant and survival library (1.5 million offline articles) that runs on your own computer, with no internet. Shows the source of every answer. Mac and Windows.
8h +8★ 1,482 - Rank 64
kache init writes rustc-wrapper once. Scripts, aliases, and CI keep running cargo. Rust, C/C++, and CUDA on Linux, macOS, and Windows.
Translation pending
8h +8★ 1,360 - Rank 65
QtPass is a free, open-source GUI for pass, the Unix password manager: GnuPG-encrypted passwords synced with Git on Linux, Windows, macOS and BSD.
8h +8★ 1,164 - Rank 66
从主题或文章制作完整手绘讲解视频：按部位描线、逐字书写、VoiceStudio 配音、五项内置制作依赖。
Translation pending
8h +8★ 1,064 - Rank 67
phi is a minimal terminal coding agent harness in Go — sub-agents, hashline edits, a permission gate, and MCP without context death.
8h +8★ 875 - Rank 68
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine writt
8h +8★ 855 - Rank 69
This is up to ~5× training speedup, with native NVIDIA GPU and Kunlun XPU support. It is modular and scalable, from Baidu Baige.
AI translation
8h +8★ 816 - Rank 70
Community DeepSeek Harness plugin with novel, short-drama, game and video-recap workbenches, bundling pinned versions of the four ZenStory AI skill packs.
8h +8★ 696 - Rank 71
You hold the pen. AI keeps your ink flowing. Textus is a free, open-source, next-generation Markdown editor for macOS, Windows and Linux, with a writing assistant built in.
8h +8★ 637 - Rank 728h +8★ 417
- Rank 73
Search an open database of AI, LLM, agent, multimodal and AI-for-science benchmarks, each with its own page carrying the paper, code, dataset and scores.
8h +8★ 348 - Rank 748h +8★ 170
- Rank 75
Flopwire lets your agents message each other and search each other’s history across the harnesses, models, machines, and teammates you already have. Open source and self-hostable.
8h +8★ 102
