A Collection of all Published Spectroscopic Redshifts within the COSMOS Legacy Field

The 7-Zip derivative intended for the modern Windows experience

paper to gal conversion tool

Cross-platform desktop GUI for music source separation

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

Open Frontier Intelligence

AI中转站质量监控 · 模型验真 · Token成本优化 — RelayRadar 中转雷达

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

A straightforward method for training your LLM, from downloading data to generating text.

Codex 降智测试

EhViewer overhauled with Material Design 3 and more, forked from https://github.com/Ehviewer-Overhauled/Ehviewer

A public and community-contributed catalog of known strong gravitational lenses

纯AI coding 臭弟弟。发生器P3/HDR部分使用探头已完成验证。

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

[CVPR 2026] DDT: Decoupled Diffusion Transformer

RE Engine, search file paths of pak.

AES decryption key finder for Unreal Engine 4

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

Long Video Gen Infrastructure

OpenShell is the safe, private runtime for autonomous AI agents.

Generate audiobooks from e-books

Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

VLESS+XHTTP+TLS Auto-Installer for Ubuntu — Vercel / Netlify relay

LLM Frontend for Power Users.

The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA

Custom LM Studio backends — run on legacy CPUs and Vulkan GPUs. AVX1, experimental no-AVX, and more. We were told it wouldn't work… so we made it work.

llama.cpp fork with additional SOTA quants and improved performance