Ollama 推出 ollama launch 命令，一键配置 Claude Code、Codex 等编码工具
ollama launch · Ollama Blog
Ollama 发布新命令 ollama launch，可自动设置并运行 Claude Code、OpenCode、Codex、Droid 等编码工具，支持本地或云端模型，无需环境变量或配置文件。用户需下载 Ollama v0.15+，推荐将上下文长度设为至少 64000 tokens；本地模型包括 glm-4.7-flash、qwen3-coder、gpt-oss:20b，云端模型包括 glm-4.7:cloud、minimax-m2.1:cloud、gpt-oss:120b-cloud、qwen3-coder:480b-cloud。此次更新还提供更长的 5 小时编码会话窗口。
正文
当前显示原文，中文全文译文尚未就绪。
January 23, 2026
ollama launch is a new command which sets up and runs your favorite coding tools like Claude Code, OpenCode, and Codex with local or cloud models. No environment variables or config files needed.
Download Ollama v0.15+, then open a terminal and run:
This will guide you to select models and launch your chosen integration. No environment variables or config files needed.
Supported integrations
Claude Code; OpenCode; Codex; Droid
Recommended models for coding
Note: Coding tools work best with a full context length. Update the context length in Ollama’s settings to at least 64000 tokens. See the context length documentation on how to make changes.
Local models:
glm-4.7-flash; qwen3-coder; gpt-oss:20b
Cloud models:
glm-4.7:cloud; minimax-m2.1:cloud; gpt-oss:120b-cloud; qwen3-coder:480b-cloud
Extended coding sessions
If you have trouble running these models locally, Ollama also offers a cloud service with hosted models that has full context length and generous limits even at the free tier.
With this update Ollama now offers more usage and an extended 5-hour coding session window. See ollama.com/pricing for details.
Configure only
To configure a tool without launching it immediately: