aicoding

python is all you need !

面向 AI 编程助手的嵌入式开发技能集，为大模型提供 MCU 固件开发全流程能力。涵盖多工具链构建（Keil / IAR / CMake / PlatformIO）、烧录、GDB 调试、串口监视、Modbus / CAN / VISA 协议调试、外设驱动适配及流水线编排，支持 Linux、macOS、Windows 三平台。

Engineering workflow layer for AI coding tools with specs, review, quality gates, and traceability.为 AI 编程工具提供工程化流程、质量门禁与可追溯能力。

Build a Claude Code–like CLI coding agent from scratch.

OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams, Gherkin, TDD, Multi-Model Adversarial Spec Authoring, Glossary for Domain Terms, and reusable engineering workflows. This also makes OpenSpec spec-as-source capable.

Official Implementation of "CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion"

LLM 驱动的个人知识库

Nano Claude Code - A lightweight AI code agent in Python, inspired by Claude Code and Kimi-CLI. Now you can give it a try and enjoy it plz~~

VibeGit, Track Interaction with Diffs in AI Coding

This template provides a streamlined foundation for building Model Context Protocol (MCP) servers in Python. It's designed to make AI-assisted development of MCP tools easier and more efficient.

Codex-native operating layer for repeatable AI workflows with AGENTS autoload, project-isolated memory, plugin skills, and a thin ro CLI for terminal + VS Code chat.

The aivi editor is a light weight, vi-inspired editor that harnesses the power of AI to provide prompt engineering.

a JEPA coding agent. Plan: first build reliable structured repair, then strong candidate-ranking data, then trainable models, then a JEPA-style repo-transition planner.

Codex and AiCoding skills, plugin packaging, and Git governance workflows for agent-native embedded development.

Flask authentication system with JWT, email verification & web UI - a complete example of PRP-driven development with Claude Code

Agently 旨在构建一个专注于软件开发全流程的智能编程助手，通过多智能体协作的方式，覆盖从需求分析到代码部署的完整软件开发生命周期（SDLC），为开发者提供真正实用的 AI 辅助编程体验。

AI-powered universal code generator that creates 300+ ready‑to‑run files across 20+ languages in seconds.

Implementing the MBPP benchmark evaluation on the Qwen3 model.