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 · 1,021 projects
8h + shows stars gained since the previous cycle · ★ shows total stars
Cycle Nov 13, 16:00 KST · next scheduled Nov 14, 00:00 KST
- Rank 61
An AI agent for your desktop and terminal, on any model you choose. Hosted models run on Fuel, paid in $DULUS.
8h +6★ 612 - Rank 628h +6★ 571
- Rank 63
Without training models, RoboHarness combines visual clicks, keypoint tracking, and geometric constraints to provide an embodied control panel for an LLM agent.
8h +6★ 482 - Rank 64
Open-source, local-first task manager that works offline, syncs every device, runs on a Raspberry Pi, and requires no subscription.
AI translation
8h +6★ 401 - Rank 65
The free, open-source Arc replacement for macOS. Spaces, pinned tabs, split view and Arc's shortcuts, with your Arc sidebar imported in one go.
8h +6★ 266 - Rank 66
A 2D painting and animation app with no image generator in it. Your agent paints with klad's brushes, stroke by stroke, and everything it paints stays editable, smudges and wet paint included.
8h +6★ 171 - Rank 67
botmux is a bridge: a resident daemon listens for Feishu messages and, per new topic, starts an independent AI coding CLI (Claude Code, Codex, Cursor, Gemini, OpenCode, Antigravity, etc.), renders terminal output live into Feishu streaming cards, and gives you an interactive Web terminal. Phone, computer and Feishu sync, and it follows you. Address: https
AI translation
8h +5★ 1,980 - Rank 68
Getting ADB, root, backups and custom apps onto locked-down Android photo frames (Skylight Calendar, BIUFRAME)
Translation pending
8h +5★ 1,761 - Rank 69
Noctalia is a family of native Wayland projects: a desktop shell, a compositor, and a login screen.
AI translation
8h +5★ 1,644 - Rank 70
Continue your work in a new session without restating decisions, constraints, and progress.
AI translation
8h +5★ 1,634 - Rank 71
Harvey’s Legal Agent Benchmark is an open-source benchmark built to evaluate and improve agent capabilities for supporting legal work.
8h +5★ 1,615 - Rank 72
An agent writes a scene as code, renders it on the GPU, looks at the result and revises the code. Source-available and free during the research preview.
8h +5★ 1,499 - Rank 73
Autonomous AI security testing for developers and security teams: find vulnerabilities, prove each with a working exploit, and ship verified fixes with zero infrastructure setup.
8h +5★ 1,348 - Rank 74
MSIME (Water Cedar Input Method) is an open-source Chinese input method for Windows, macOS, Linux, Android, iOS, and HarmonyOS, supporting full pinyin, double pinyin, and Wubi, with translation displayed next to candidate words. View download, user guide, and FAQ.
AI translation
8h +5★ 1,287 - Rank 75
Inspect apps, binaries and runtime behavior with your coding agent or terminal. REA connects local analysis tools through CLI and MCP.
8h +5★ 1,275
