Agents.json – OpenAPI Specification for LLMs
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…
Agents.json – OpenAPI Specification for LLMs launched on March 3, 2025 with 212 votes, #183 of 7,215 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
Agents.json is an open specification that enables large language models to discover and invoke APIs using natural language. Built on the OpenAPI standard, it consists of an agents.json file that defines how API calls connect into outcome-based tools, plus an SDK that loads these files for LLM execution. The specification aims to standardize how LLMs interact with APIs in a reproducible, observable way, allowing developers to avoid manually implementing API integrations for each AI application.
written from the facts on this page · September 2026
From the sources
Contribute to wild-card-ai/agents-json development by creating an account on GitHub.
The agents.json Specification is an open specification that formally describes contracts for API and agent interactions, built on top of the OpenAPI standard. The current version is 0.1.0 . Use the Wildcard Bridge Python package to load, parse, and run agents.json. The agents.json Specification is an open specification that formally describes contracts for API and agent interactions, built on top of the OpenAPI standard. Give feedback, share your projects, and get help in our Discord . Enabling AI agents to interact with APIs is difficult. We faced the same problem as many others building agents: altering APIs to work reliably with LLMs and executing multiple API calls successfully in a row…from github.com
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
OpenUIMar 2026 · openui.com · ▲322Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Open Envelope – an open schema for defining AI agent teamsMay 2026 · openenvelope.org · ▲52Built an open JSON Schema for defining AI agent teams. Multi-agent systems are becoming a real deployment pattern — not single assistants, but teams with roles, handoffs, and human checkpoints. But there's no shared way to define one that travels across frameworks. Every implementation is scattered, locked to whichever tool you picked first. Built the schema to fix that. The schema lives at schema.openenvelope.org and is registered in SchemaStore, so if you drop a .envelope.json file in VS Code you get autocomplete and validation without installing anything. It's also on npm as…
Api2ai – create an API agent from any OpenAPI Spec2023 · github.com · ▲23api2ai parses OpenAPI Spec to generate an agent that can make API calls. For context, I recently need to explore a handful of API suites and thought LLMs can help expedite this process. After some digging, I found OpenAPI Specs are perfect fit for function calling. Based on a text prompt, api2ai can select the right endpoint and properly parse request params and make api calls. It also handles authentication, currently it supports basic auth, api keys, and bearer token schemes. The tool has helped me explore and see APIs in action without a deep dive into the docs or using postman. It’s open…
Open Codex – OpenAI Codex CLI with open-source LLMs2025 · github.com · ▲106Hey HN, I’ve built Open Codex, a fully local, open-source alternative to OpenAI’s Codex CLI. My initial plan was to fork their project and extend it. I even started doing that. But it turned out their code has several leaky abstractions, which made it hard to override core behavior cleanly. Shortly after, OpenAI introduced breaking changes. Maintaining my customizations on top became increasingly difficult. So I rewrote the whole thing from scratch using Python. My version is designed to support local LLMs. Right now, it only works with phi-4-mini (GGUF) via…
Use LLMs to Interact with APIs2024 · github.com · ▲35Recently featured in a LangChain blog https://blog.langchain.dev/empowering-development-with-flowt... , use LLMs to construct an API first runnable workflow with an IDE experience.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
