Discover new repositories and follow their star growth.
Time filters select when repositories were created. Growth uses recorded daily star counts.
1,000 results (GitHub search limit)
The fastest and litest LLM chating ui with 2 fields, less than 100 kb and completely no dependent.
End-to-end retail analytics and recommendation platform using PySpark, Kafka, PostgreSQL, Power BI, PyTorch Two-Tower, Qdrant, FastAPI, Docker and Azure.
Reusable prompts for a structured, evidence-first bug bounty hunting workflow
Kantor Kita: interactive 3D paper-model office for a 13-person team
zkm27 fully deobf, renamed, optimized, and ideaready.....
Evolving Multimodal Inference Programs: LLM-guided evolutionary search for accurate and efficient vision-language inference.
GLM-5.3-Flash (abliterated EXL3) on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8x faster decode than vLLM, 4x256k concurrent threads, byte-exact speculative decoding. Work in progress.
Standalone Codex skill for MiniMax H3 Colab reference-to-video generation
Unofficial native ARM64 Beat Saber for the Steam Frame / ARM64 Proton: no FEX, no frame drops.
An Agent Skill: drive Cline CLI coding tasks as the user's proxy.
Tame3D research framework: evidence-grounded multi-agent 3D reasoning with scene-level conformal uncertainty alignment
OW Bridge — 让 WorkBuddy 使用 OpenCode 免费模型。支持 macOS / Windows，自动发现模型、一键导入。
Decompilation of Serial Experiments Lain (PlayStation) and a native Windows, macOS and Linux client
Heapscape: a local Three.js and ClrMD explorer for .NET memory dumps
ONCE Campfire in Rust: one binary, the Rails app's data, 19–44× faster
