Show HN: Agents.json – OpenAPI Specification for LLMs

📰 Hacker News · yompal

Learn how Agents.json enables LLMs to discover and invoke APIs with natural language using the OpenAPI standard

intermediate Published 3 Mar 2025

Action Steps

Define an agents.json file to describe API calls for LLMs
Load the agents.json file using the Agents.json SDK
Execute API calls as a series of outcome-based tools for LLMs
Test and refine the agents.json file for optimal performance
Use the OpenAPI standard to ensure compatibility and observability

Who Needs to Know This

Developers and engineers working with LLMs and APIs can benefit from this specification to create more flexible and non-deterministic workflows

Key Insight

💡 Agents.json enables LLMs to be non-deterministic and flexible in their workflows, reducing the need for hard-coded implementations

Key Takeaways

Learn how Agents.json enables LLMs to discover and invoke APIs with natural language using the OpenAPI standard

Full Article

Hey HN, we’re building an open specification that lets agents discover and invoke APIs with natural language, built on the OpenAPI standard. agents.json clearly defines the contract between LLMs and API as a standard that's open, observable, and replicable. Here’s a walkthrough of how it works: https://youtu.be/kby2Wdt2Dtk?si=59xGCDy48Zzwr7ND . There’s 2 parts to this: 1. An agents.json file describes how to link API calls together into outcome-based tools for LLMs. This file sits alongside an OpenAPI file. 2. The agents.json SDK loads agents.json files as tools for an LLM that can then be executed as a series of API calls. Why is this worth building? Developers are realizing that to use tools with their LLMs in a stateless way, they have to implement an API manually to work with LLMs. We see devs sacrifice agentic, non-deterministic behavior for hard-coded workflows to create outcomes that can work. agents.json lets LLMs be non-deterministic for the outcomes they w

Read full article → ← Back to Reads