Lists (3)
Stars
The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS
RoguePlanet Windows Defender Vulnerability
Anbeeld / beellama.cpp
Forked from spiritbuun/buun-llama-cppDFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM
Dynamic context pruning plugin for OpenCode - intelligently manages conversation context to optimize token usage
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
An agentic skills framework & software development methodology that works.
🌱 Private, quiet space for thinking. Simple app for .md files. LLM-friendly.
26m function call model that runs on incredibly small devices
Copy Fail 2: Electric Boogaloo
PoC: fully unprivileged container escape to node-level code execution on Kubernetes via CVE-2026-31431 page-cache corruption + shared image layers. Validated on Alibaba Cloud ACK, Amazon EKS and Go…
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Reverse Engineering: Decompiling Binary Code with Large Language Models
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
Muon is an optimizer for hidden layers in neural networks
Copy Fail (CVE-2026-31431): 9-year-old Linux kernel LPE found by Theori's Xint Code
ML-powered manga translator, written in Rust.
Fast LLM speculative inference server for consumer hardware.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels