将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

A collaborative effort to build the leanest circuit that breaks ECDSA

Zero Knowledge Proof for resource estimates of Elliptic Curve Point Addition Quantum Circuits.

A collaborative effort to build the leanest circuit that breaks ECDSA

A collaborative effort to build the leanest circuit that breaks ECDSA

Bartosz Milewski 的 '写给程序员的范畴论' 非官方 PDF and LaTeX source 的中文翻译

收集和整理的可靠Claude中转API资源列表，帮助开发者快速找到稳定、高性价比的Claude API服务

Minimalistic 4D-parallelism distributed training framework for education purpose

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

A from-scratch Prefill/Decode disaggregation inference engine for LLMs

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Achieve state of the art inference performance with modern accelerators on Kubernetes

AI agents running research on single-GPU nanochat training automatically

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

Twitter API Scraper | Without an API key | Twitter Internal API | Free | Twitter scraper | Twitter Bot

No fortress, purely open ground. OpenManus is Coming.

A live stream development of RL tunning for LLM agents

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Model Context Protocol Servers

A collection of MCP servers.

The math library of Lean 4

Simple RL training for reasoning

Minimal reproduction of DeepSeek R1-Zero

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Kolmogorov-Arnold Network for Reinforcement Leaning, initial experiments

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training