Linux (Ubuntu 24.04/26.04 or OpenWrt) next to Android on the ZTE F50 / MU300 and U30 Air 5G hotspots (Unisoc T760 / UMS9620): installer, vendor 5.4 and mainline 6.18 / 7.2 kernels, 5G modem, Wi-Fi,…

A functional tools for z*e devices (F50 | U30 Air)

Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

An agentic skills framework & software development methodology that works.

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

⚠️ Moved to https://github.com/brainana/brainana — this repo is no longer maintained.

An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read.

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

Open-source, low-cost 10.5 GHz PLFM phased array RADAR system

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…

The programming language for agents

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

"AI-Trader: 100% Fully-Automated Agent-Native Trading"

mcts-simple is a Python3 library that implements Monte Carlo Tree Search and its variants to solve a host of problems, most commonly for reinforcement learning.

Implementation of Dreamer v3 in pytorch.

Scalable metrics logging and analysis

Building blocks for productive research

concurrent frame capture with USB webcams

The open source coding agent.

Neovim config for the lazy

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)

Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-…

🚀 The fast, Pythonic way to build MCP servers and clients.

Connect AI models like Claude & GPT with robots using MCP and ROS.

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, P…

Abstraction layer for painlessly building object oriented distributed systems that just work