Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 1314 |
| 2026-08-06 | 1314 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <source srcset="./static/logo/agentsjson-white-blackbackground.png"> <img alt="Shows a white agents.json Logo with a black background." src="./static/logo/agentsjson-white-blackbackground.png" width="full"> </p> <h1 align="center"> Translate OpenAPI into LLM Tools</h1> [](https://github.com/wild-card-ai/agents-json/stargazers) [](https://discord.gg/7VU6HKq7cZ) [](https://docs.wild-card.ai/agents-json) [](https://x.com/wildcard_ai) 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. ## Quickstart <p align="center"> <img align="center" src="./static/quickstart/3easysteps.png" alt="Wildcard Bridge" width="700"> </p> ### Use one of the quickstart notebooks to get started: | Agent | Auth | Notebook | | --- | --- | --- | | [Resend](./examples/resend.ipynb) | API Key | `./examples/resend.ipynb` | | [Stripe](./examples/single.ipynb) | Bearer Token | `./examples/single.ipynb` | | [Rootly](./examples/rootly.ipynb) | Bearer Token | `./examples/rootly.ipynb` | | [Twitter + Giphy](./examples/multiple.ipynb) | OAuth 1.0, API Key | `./examples/multiple.ipynb` | | [Resend + Hubspot + Google Sheets](./examples/multiple-dynamic.ipynb) | OAuth 2.0, API Key | `./examples/multiple-dynamic.ipynb` | ## Demos | | | | --- | --- | | [Stripe Agent](https://demo.wild-card.ai/stripe) | [<img src="./static/demo/stripe-demo.png" alt="Stripe Agent" width="300">](https://demo.wild-card.ai/stripe) | | [Google Sheets Agent](https://demo.wild-card.ai/googlesheets) | [<img src="./static/demo/googlesheets-demo.png" alt="Google Sheets Agent" width="300">](https://demo.wild-card.ai/googlesheets) | | [Resend Agent](https://demo.wild-card.ai/resend) | [<img src="./static/demo/resend-demo.png" alt="Resend Agent" width="300">](https://demo.wild-card.ai/resend) | | [Rootly Agent](https://demo.wild-card.ai/rootly) | [<img src="./static/demo/rootly-demo.png" alt="Rootly Agent" width="300">](https://demo.wild-card.ai/rootly) | ## agents.json Specification 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`. Give feedback, share your projects, and get help in our [Discord](https://discord.gg/7AP6wSkVt). ### Schema The full schema is available [here](https://docs.wild-card.ai/agentsjson/schema). ### Motivations 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 is a trial and error process. APIs are designed for developers and not LLMs. If you're building integrations for AI agents, you need to write boilerplate, experiment with system prompts, optimize tool definitions, and parse responses into vector stores - for each API. For example, the Gmail API has endpoints to search for threads, list the emails in a thread, and reply with an email given base64 RFC 822 content. Instead, LLMs need a clear, top-level directive that can handle all of this with one tool. <p align="center"> <img style="text-align: center;" src="./static/diagram/TraditionalFlowDiagram.png" alt="Traditional API Paradigm" width="full" title="Traditional API Paradigm"> </p> **Why is `agents.json` built on OpenAPI?** — OpenAPI is the gold standard for descr
Excerpt of 11,246 characters
Read on GitHub
41
26
8
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1e3153f160976ef8, llm:No README or topics provided; repository name 'agents-json' under organization 'wild-card-ai' suggests tooling for agents using JSON—likely agent definitions or orchestration for AI agents.
matched fp:1e3153f160976ef8, llm:No README or topics provided; repository name 'agents-json' under organization 'wild-card-ai' suggests tooling for agents using JSON—likely agent definitions or orchestration for AI agents.
