用 Amazon Bedrock 开源权重模型驱动 AI 编码代理
原标题：Use open weight models as your AI coding agent with Amazon Bedrock
AI 摘要
AWS Machine Learning Blog 介绍如何将开源权重模型与开源终端 AI 编码代理 OpenCode 结合，通过 Amazon Bedrock 在自有 AWS 账户内运行推理，避免数据外发、供应商锁定和按席位收费。文章给出配置方法、多模型工作流，并以 Moonshot AI Kimi K3、OpenAI GPT-OSS 120B、NVIDIA Nemotron 3 Super 120B 为例演示编码场景，同时提到 Ethara.AI 已在生产中使用该架构进行多代理编排。
正文节选
Use open weight models as your AI coding agent with Amazon Bedrock AI coding agents have become a core part of how developers write, debug, and refactor software. Open weight models on Amazon Bedrock now make these agents practical to run privately and cost-effectively. But most options require you to send your proprietary data to a third-party API, lock you into a single model provider, or charge per-seat subscriptions regardless of how much you use them. If you have data residency requirements