Ollama 与 Fly.io 合作推出 Connector，让 AI 智能体在 Sprite 沙箱中安全运行
Run AI agents safely with Ollama and Fly.io · Ollama Blog
Ollama Cloud 现已可在 Fly.io Sprites 的完整 Linux 虚拟机中运行，Claude Code、Codex 和 Gemini CLI 开箱即用。新增的 Ollama Connector 让 Sprite 通过 Fly.io 网关调用 kimi-k3、glm-5.3 和 deepseek-v4.1-flash 等云端模型，API key 由 Fly.io 加密保存，Sprite 只持有网关 URL 和连接 ID，因此无法泄露密钥。新连接器默认屏蔽所有 Sprite，可按标签、名称前缀或全部开放，调用仅限 Sprite 内部发起。
推荐理由
AI 评分 55
原文给出 Ollama Connector 在 Fly.io Sprite 沙箱中的密钥隔离机制与接入步骤，可据此评估智能体安全运行方案。
主题
正文
当前显示原文，中文全文译文尚未就绪。
October 13, 2026
Ollama Cloud now works inside full Linux computers designed for agents using Fly.io Sprites.
A Sprite is a sandbox from Fly.io. Each one is a full Linux virtual machine with its own disk that stays around between sessions. Claude Code, Codex and Gemini CLI are supported out of the box and will let agents run in a sandbox to securely run commands.
With the new Ollama Connector, your Sprites can use Ollama’s cloud models like kimi-k3, glm-5.3 and deepseek-v4.1-flash.
How it works
You add your Ollama API key to your Fly.io organization, and Fly.io encrypts it and never returns it through the API.
When code inside a Sprite calls Ollama, it goes through a Fly.io gateway. The gateway checks which Sprite is calling and adds your key to the request. The Sprite itself only knows a gateway URL and a connection ID.
This means:
An agent in a Sprite can’t leak your key; New connectors block every Sprite by default. You choose which ones get access: by label, by name prefix or all of them; Calls only work from inside a Sprite
You’ll need an Ollama API key and at least one Sprite.
In the Fly.io dashboard, open Sprites, then Connectors, and add an Ollama connector with your API key; Under Access Configuration, choose which Sprites can use it and save; Click Test reachability next to a Sprite to check that it can reach Ollama
Then, from inside the Sprite:
The connector page shows this command with your connection ID filled in. There’s no Authorization header because the gateway adds your key.
Python
Any OpenAI SDK works. Set base_url to the gateway and use any value for api_key:
Ollama’s native /api/* routes work through the gateway too.
Coding agents
Fly.io Sprites come with a skill that tells Claude Code, Cursor, Codex and Gemini CLI about Ollama. If the Sprite has access, the agent can use Ollama models without any setup.
Example: fuzzing
Fly.io has a guide that uses several models together. A small model like nemotron-3-nano:30b writes malformed inputs, a Sprite runs them against your program, and a larger model like kimi-k3 looks at the crashes. To switch models, change the model field. See the Ollama Connector quickstart.
Thank you to the Fly.io team for building this with us.
Ollama Connector quickstart on Fly.io; Ollama Cloud models; Ollama pricing