A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.

TripoSR: Fast 3D Object Reconstruction from a Single Image

GPU-driven real-time FFT ocean (Three.js + WebGPU/TSL)

Unlocking _everything_ on the CPU with DRAM scrambling

Physical game cartridges with 2.5" SSDs for your Steam/GoG/Local library

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Procedural spider that walks, climbs walls, and leaps onto any terrain. Analytic IK legs, a flexible articulated body, wall-latching. Three.js, no rig or animation clips.

A three.js agent skills for producing awesome graphics for scenes and games

Parakeet implementation in C++ with ggml

The best ChatGPT that $100 can buy.

Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.

The comprehensive guide for online anonymity and OpSec.

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Generate Git commit messages directly from VS Code Source Control using a local/offline AI model via Ollama, LM Studio, or any OpenAI-compatible endpoint.

BLXCode is an open-source desktop workbench for running AI coding agents beside real terminals, project memory, tasks, and an embedded browser. It is built with Tauri 2, Rust, Leptos, and Trunk.

Have a natural, spoken conversation with AI!

Your First LLM-Wiki Conversation Knowledge Base

An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault

Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secrets detection, IaC + CI hardening, and a read-only auditor subagent. MIT.

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.

Open Usage — monitor your Claude and Codex AI token usage

A benchmark that challenges language models to code solutions for scientific problems

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Autonomous experiment loop extension for pi