qwen-cli

OpenSkills: Run Claude Skills Locally using any LLM

An open-source, graph-based workflow engine for Gemini/OpenCode/Claude Code/Qwen CLI. Automate ML experiments and scientific discovery.

Force any OpenAI-compatible or Anthropic API-compatible tool (Claude Code, Qwen Code, Aider, Fabric, Interpreter) to use Gemini, Groq, Cerebras, or Ollama. Pure Bash. Zero dependencies.

A complete Windows setup guide for running Claude Code with free Qwen models using PowerShell, including token setup, router configuration, and seamless coding workflow.

An **MCP server** for the Gemini CLI that analyzes a local code repository (and helps generate and maintain a high‑quality `ONBOARDING.md` guide.

Portability + coordination layer for multiple AI CLIs: write a skill once and run it in Claude, Gemini, Qwen, iFlow, Qoder, CodeBuddy, Codex, KiloCode, and opencode — and share session context across CLIs.

A structured AI agent workflow template for software teams — reduces hallucination, controls token usage, and keeps output consistent across sessions and models

Coding-agent session manager: search Copilot CLI history and Claude Code/Codex conversations; resume saved context; try focusing a matching running Windows Terminal tab. Qwen, Gemini and Kimi history too. Default grouping sends session titles and working directories remotely; set Core + wordmatch before launch.