Qwen Code has released a multi-protocol agent runtime that allows users to switch between various large language models, including OpenAI, Anthropic, Gemini, Qwen APIs, and local models like Ollama and vLLM, without restarting their sessions. This runtime features a provider abstraction layer that normalizes tool definitions and response formats across different LLM APIs, ensuring compatibility. Key components include a provider registry, tool schema normalizer, response parser, and a state manager that persists conversation history and tool results in a local SQLite database. The system also incorporates Auto-Memory for persistent conversation history and user preferences, Auto-Skills for runtime generation of new tool definitions based on repeated workflows, and SubAgents and Agent Teams for nested orchestration of tasks. AI
IMPACT Enables developers to easily integrate and switch between various LLM providers within a single application, streamlining development workflows.
RANK_REASON The item describes a software tool that integrates with existing LLM providers, rather than a new model release or core research from a frontier lab.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
