DeepSeek Harness: Everything is a Plugin.

Binance Skills Hub is an open skills marketplace that gives AI agents native access to crypto

AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi…

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

Public repository for Agent Skills

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

TokenSpeed is a speed-of-light LLM inference engine.

[TMLR 26] EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Open-source, community-driven agent harness

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Agent Skills for Google products and technologies

Drogon: A C++14/17/20 based HTTP web application framework running on Linux/macOS/Unix/Windows

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

OpenAI Privacy Filter

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

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

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Official repository for "AM-RADIO: Reduce All Domains Into One"

IronClaw is an Agent OS focused on privacy, security and extensibility

GLM-OCR: Accurate × Fast × Comprehensive

[RSS 2026] Causal video-action world model for generalist robot control

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Visual Causal Flow

a embedding infer server faster than vllm and sglang