Star velocity · weekly
GitHub trending repositories by snapshot date
Explore dated GitHub trending snapshots, compare star activity, and read repository profiles before choosing a project.
Latest weekly snapshot · September 7, 2026
- 1
ayghri/i-have-adhd : Stop your coding agent from burying the answer
PythonInstalls as a skill for Claude Code and similar assistants and changes how they reply: the answer comes first, multi-step tasks are numbered, and every reply ends with one concrete next step. Useful when long agent responses make you hunt for the actual fix; its rule file is plain text, so you can tune the behavior yourself.
+16,980 - 2
bilawalsidhu/gods-eye-view : Follow flights and ships around an interactive 3D Earth
JavaScriptA browser-based 3D globe that combines public feeds such as aircraft, ships and earthquakes. Following an aircraft across the terrain is an engaging way to explore geographic data; its visual sensor effects should not be confused with actual sensor imagery.
+13,398 - 3
tt-a1i/archify : Show your team exactly what changed in the architecture
JavaScriptTurns an agent's structured description of a system into interactive HTML and SVG architecture diagrams. It can compare diagram snapshots, useful for showing a team which components and connections changed between two versions of a design.
+9,548 - 4
deepseek-ai/deepseek-harness : Explore DeepSeek's building blocks for an extensible agent
TypeScriptDeepSeek's agent runtime built around replaceable plugins, with a web interface for running it. Useful for developers exploring how to compose an agent's capabilities; it is a developer preview, so expect interfaces to change as you experiment.
+8,535 - 5
DietrichGebert/ponytail : Stop your AI turning a small fix into a new framework
JavaScriptA set of instructions that asks AI coding agents to reuse existing code and question whether a new abstraction is needed. Its rules also explicitly retain validation and error handling, useful when your agent keeps making a small task unnecessarily complicated.
+7,635
Latest daily snapshot · September 15, 2026
- 1
alibaba/open-code-review : Put AI review comments on the lines that need attention
GoReviews code changes with an AI model and places comments on the relevant lines. File selection and comment positioning are handled by ordinary program logic, useful when you want review suggestions that are easier to locate and check in a large diff.
+2,090 - 2
JustVugg/colibri : Run 700-billion-parameter MoE models on hardware you already own
CA pure C inference engine with zero dependencies that streams the experts of giant mixture-of-experts models from disk, treating VRAM, RAM and storage as a single memory hierarchy. It runs models from 744B up to 2.8T parameters on consumer hardware, and a built-in web dashboard shows which expert tiers are active while you chat.
+1,791 - 3
debpalash/VoiceStudio : Try voice design, transcription and dubbing in one workspace
PythonA local audio workspace for voice design, transcription, dubbing and longer narrated projects. Useful for trying several speech workflows with your own material in one application, with engine choice and hardware determining the supported languages and output quality.
+1,776 - 4
bojieli/ai-infra-book : A book that derives LLM system design from hardware limits
PythonAn open manuscript of a Chinese book on AI infrastructure that derives LLM inference and training design from hardware capacity, bandwidth, and model architecture, using order-of-magnitude estimates instead of generalities. The repo carries the full draft, a typeset PDF rebuilt on every update, and companion experiments and calculation tools.
+1,232 - 5
bilawalsidhu/gods-eye-view : Follow flights and ships around an interactive 3D Earth
JavaScriptA browser-based 3D globe that combines public feeds such as aircraft, ships and earthquakes. Following an aircraft across the terrain is an engaging way to explore geographic data; its visual sensor effects should not be confused with actual sensor imagery.
+1,211
How to read these rankings
Numbers come from GitHub's official stargazers/history endpoint: the stars each repository gained on each day of the window. GH Archive only supplies candidates; every count is re-read from GitHub. This is not GitHub's own Trending ranking.
How this differs from GitHub's own Trending page: GitHub does not rank purely by stars gained. It rotates projects and weighs other signals, so a repository climbing for five days straight drops off its list while still leading this one, and a project gaining two hundred stars a day can appear there and not here. These lists are ordered by one thing: stars gained during the window. The same data, asked a stricter question.
Each list carries its snapshot date. Archives preserve the recorded activity rather than showing a live ranking. Attention can identify projects to investigate; it does not establish code quality, security, or maintenance.
Open a daily or weekly snapshot for the full list, then read a repository profile for its license, setup requirements, and limitations. Check recent commits and issues in the upstream repository before adopting it.