ProductsSelected

LangChain 推出 LangSmith Tool Gateway 公测:为 Agent 工具调用提供三层管控

Why we picked it

LangChain 给 Agent 的工具调用加了个统一管控层,凭据、权限、审计全走网关。跑生产 Agent 的团队都遇到过它乱调工具的问题,现在可以在 LangSmith 平台上配三层规则,不用自己在代码里堆权限判断,做 Agent 运维的可以看看。

LangChain 宣布 LangSmith Tool Gateway 进入公开测试阶段,托管在 LangSmith Agent Platform 上。该产品是一个托管的工具层,统一处理 Agent 每次工具调用涉及的凭据、身份和访问权限,目标是防止 Agent 执行未经授权或非预期的操作。

Body

产品提供三层治理机制:Access 层管理凭据与身份认证,Control 层约束 Agent 和用户实际可执行的动作范围,Visibility 层提供对工具调用行为的审计可见性。开发者无需在业务代码中自行拼装权限逻辑,而是通过这个网关层集中配置。

对在生产环境跑 Agent 的团队来说,工具调用失控是常见落地障碍,这一层治理能力补上了 LangSmith 平台在安全与合规侧的缺口,也和直接给 Agent 裸调 API 的做法形成区分。

Original · LangChain

Agents can often take unauthorized and unintended actions. LangSmith Tool Gateway is built to ensure that agents and users can only do the things you intend across 3 layers of governance. 1️⃣ Access 2️⃣ Control 3️⃣ Visibility Ready to get started? LangSmith Tool Gateway is now available in Public Beta on the LangSmith Agent Platform. LangChain @LangChain Introducing LangSmith Tool Gateway, a managed tool layer that handles credentials, identity, and access for every tool call an agent makes, making it simple to govern the actions your agents take. 💻 Learn more: langchain.com/blog/langsmith… Y

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LangSmith, LangChain, agents, AI safety.

Source attribution: curated from LangChain (@LangChainAI).