Popular projects
2,000 to under 100,000 GitHub stars · most stars first within each tier · Methodology
★ 2,000–under 5,000 · Developer tools · 499 projects
Green numbers beside ★ are stars gained since the previous check · Most stars
- Rank 106★ 3,972
- Rank 107
External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.
★ 3,968−1 - Rank 108
TanStack DB gives you a reactive, client-first store for your API data with collections, live queries and optimistic mutations that keep your UI reactive, consistent and blazing fast 🔥
★ 3,968+4 - Rank 109
A lightweight, powerful framework for multi-agent workflows and voice agents
★ 3,955+2 - Rank 110
Free, open-source 3D Gaussian Splatting (3DGS) software. Train, edit, and render Gaussian Splats locally on your GPU — Python plugins, MCP, Windows & Linux.
★ 3,937+6 - Rank 111★ 3,933−1
- Rank 112
State-of-the-art LLM compression, built for production inference with vLLM
★ 3,928+2 - Rank 113★ 3,927
- Rank 114★ 3,916
- Rank 115
Context engineering for AI coding agents. 10 read modes, 95+ shell patterns, 27 languages. 221k+ installs.
★ 3,911+5 - Rank 116
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
★ 3,893+31 - Rank 117
The open-source catalog of JSON schemas for editors and tools, with support for JSON, YAML, and TOML files.
★ 3,877+1 - Rank 118
The industry's first multi-user, multi-agent, real-time collaboration space — parallel editing, agent borrowing, no-deploy sharing.
Translation pending
★ 3,875+2 - Rank 119
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependenc
★ 3,857+18 - Rank 120★ 3,842+2
