档案库 · AI 与模型 · 产品决策 · 2025-2026
Wildcard AI押注agents.json，为LLM打造的OpenAPI层，成为智能体调用API的方式
Wildcard AI押注agents.json，一个无状态的OpenAPI层，成为LLM调用API的标准；2025年3月Show HN，1.3k星，YC支持
Wildcard AI
做的是什么生意
Wildcard AI builds developer infrastructure for agent-API integration: the open-source agents.json specification (an OpenAPI layer that describes tools, flows and links for LLMs), a Bridge Python package that loads and runs the contracts, and a public registry of agents.json files; its stated plan is to charge API providers for white-glove onboarding onto the standard.
起因
Wildcard AI started agents.json as an internal config file while building an agent with access to Gmail: putting the full API spec into the LLM's context gave poor accuracy in tool selection and tool calling, even with the output space cut to 5-10 endpoints, and the team concluded APIs are designed for developers, not LLMs. The file grew features like auth registration and tool search; when HubSpot CTO Dharmesh posted publicly about the concept of a specification that translates APIs for LLMs, Wildcard decided to open-source what it already had working. On the launch thread the founders described going through Y Combinator with a tool-search product, and the Show HN for agents.json went up on 2025-03-03.
经过
The Show HN drew 212 points and 69 comments on 2025-03-03. The thread debated how agents.json differs from Anthropic's Model Context Protocol - stateless contracts any client can run versus stateful per-client connections - where it overlaps OpenAPI's Arazzo workflow spec, and how to license the tooling; Wildcard replied that its main opportunity is charging API providers for white-glove onboarding, kept the spec under Apache 2.0 and the Bridge package under AGPL, and said the long-term goal was to align with Arazzo. The launch post counted 10 vetted API integrations, some official, with Resend, Google Sheets, Slack and Stripe demos. By the 2026-09-05 snapshot the repository had 1.3k stars, 66 forks and 75 commits, a registry of available agents.json files, quickstart notebooks, and a roadmap still listing OAuth, loops, conditionals and failure handling as not yet built.
还没有结局，它还在跑。
背景
Wildcard AI的agents.json在团队构建可访问Gmail的智能体时作为内部配置文件启动。将完整API规范放入LLM上下文在工具选择和工具调用上准确率不佳，即使将输出空间缩减到5-10个端点，团队认为API是为开发者设计的，而非LLM——因此它开始描述如何将API调用链式组合为基于结果的工具，并在内部使用该文件，同时增加认证注册和工具搜索功能。
Wildcard在HubSpot CTO Dharmesh公开提及翻译API供LLM使用的规范概念后，开源了agents.json 0.1.0——这听起来像团队内部已有的功能。Show HN于2025-03-03上线，获得212分和69条评论，主要讨论规范与有状态的Model Context Protocol以及OpenAPI的Arazzo工作流规范的关系；Wildcard表示计划是向API提供商收取白手套接入标准的费用。
截至2026-09-05快照，仓库已有1.3k星、66个fork、75次提交，以及可用agents.json文件的注册表和针对API（如Resend和Rootly）的快速入门笔记本。规范仍为0.1.0版，OAuth、循环、条件语句和失败处理仍在路线图上，此处审查的公开材料未披露任何融资或营收数据。
这件事要成立，得有什么
- 团队自己的Gmail智能体证明，即使只有5-10个端点，原始OpenAPI在上下文的情况下在工具选择上也会失败，因此问题具体而非假设
- OpenAI的Operator预示着智能体在网络行动上的转变，而API已经在为规模而构建的后端基础设施上运行——比浏览器自动化更安全
- MCP的有状态逐客户端连接看起来不适合网络产品，留下无状态契约的空间，可在无服务器基础设施上部署
- OpenAPI给了agents.json免费分发：提供商已维护规范，旁加一个文件成本低，注册表可通过口碑增长
可借鉴之处
标准通过比现状更便宜的采用来获胜：基于提供商已维护的规范构建，保持无状态以便在任何地方运行，并通过接入路径而非协议货币化
后续进展
截至2026-09-05，agents.json仍为0.1.0版，明确是寻求社区意见的工作进展，仓库1.3k星，路线图列出OAuth支持、循环、条件语句和失败处理未完成。Wildcard AI仍然维护规范、Bridge包和公共注册表，公开材料未披露资金或营收数据。
资料来源
发现哪里写错了？告诉我们。
轮到你了
你刚读完一家。说说你在做什么，看看谁在赌同一件事。
免费账号 · 3 次免费提问 · 不用绑卡