Skip to content
View Infatoshi's full-sized avatar

Highlights

  • Pro

Block or report Infatoshi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Minecraft: Java Edition 26.3 rewritten from scratch in Rust, checked against vanilla with 281 differential harnesses. Get it with the Horizon launcher.

Rust 11,106 1,850 Updated Nov 17, 2026

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Python 26,166 3,225 Updated Nov 3, 2026

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 466,234 114,085 Updated Nov 17, 2026

Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh

TypeScript 25,302 802 Updated Nov 17, 2026

WheelWizard, Retro Rewind Launcher

C# 917 64 Updated Nov 10, 2026

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

Python 17,271 1,716 Updated Nov 16, 2026

Custom Minecraft Classic / ClassiCube client written in C from scratch (formerly ClassicalSharp in C#)

C 2,094 351 Updated Nov 17, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 282,971 35,072 Updated Nov 17, 2026

⌥ Coding agent with the IDE wired in. Built by Stencil Labs.

TypeScript 39,310 4,503 Updated Nov 17, 2026

Open-source Dreamer world-model implementation in JAX

Python 398 33 Updated Aug 5, 2026

ccache – a fast compiler cache

C++ 3,003 609 Updated Nov 15, 2026

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Python 7,318 702 Updated Jul 9, 2026

Language model tokenization at GB/s

Rust 4,157 226 Updated Nov 2, 2026

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Rust 27,801 5,247 Updated Sep 29, 2026
C++ 11,370 4,876 Updated Nov 17, 2026

Box3D is a 3D physics engine for games

C 6,792 388 Updated Nov 17, 2026

slime is an LLM training framework for RL Scaling.

Python 8,840 1,368 Updated Nov 5, 2026

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Python 1,904 140 Updated Sep 24, 2026

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

Rust 32,534 2,454 Updated Nov 17, 2026

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

Swift 28,811 2,678 Updated Nov 17, 2026

Official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

C++ 35,549 6,419 Updated Nov 17, 2026

extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

Python 1,354 115 Updated Oct 7, 2026

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python 64,867 11,161 Updated Nov 12, 2025

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

TypeScript 122,558 15,809 Updated Nov 17, 2026

NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.

Rust 4,065 375 Updated Nov 17, 2026

Orchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for.

Swift 24,684 2,125 Updated Nov 17, 2026

Universal AI coding proxy. Use Claude Code, Codex CLI, or any tool with DeepSeek, GLM, MiniMax, and more—without rate limits breaking your flow.

Rust 29 5 Updated Nov 16, 2026

Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.

Python 375 96 Updated Nov 12, 2026

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Python 1,210 96 Updated Nov 17, 2026
Next