Search

More Filters

Show More
Add Listing
Go Back

agentic web protocol

0
Web & Internet Agents
Report

Report Abuse

Basic Information

This repository defines the Agentic Web Protocol (AWP), a specification and Python tooling to make websites and APIs discoverable and reliably usable by AI agents. It provides a web page protocol based on optional ai-* HTML attributes that annotate meaningful and interactive elements with descriptions, available interactions, prerequisites, next features and states. It provides an API protocol that standardizes a /ai-handshake endpoint which returns an OpenAPI-compliant documentation of the hosting API. The project also distributes a Python AWP tool and an optional Universal Tool integration that parse annotated HTML or call /ai-handshake to produce machine-readable documentation in YAML or JSON. The README includes installation instructions, usage examples, a playground, and cross-platform guidance for cloud, desktop, web and mobile environments.

Links

Stars
12
App URL
https://github.com/blueraai/agentic-web-protocol
Github Repository
https://github.com/blueraai/agentic-web-protocol/blob/main/README.md

Categorization

App Details

Features
The repo documents standard ai-* parameters for HTML such as ai-description, ai-interactions, ai-prerequisite-<interaction>, ai-ref, ai-next-<interaction>, and ai-state and specifies when each should be present. For APIs it defines a required /ai-handshake GET endpoint that returns OpenAPI documentation in JSON or YAML. The Python awp package exposes parse_html and parse_api functions and a UniversalTool class with parse_html and parse_api methods that return documentation and optional logs. Outputs support YAML (default) or JSON formats and the README provides example input/output, a ready-made playground script, pip install instructions and guidance on integrating the AWP Tool into AI agents and Universal Tools.
Use Cases
AWP helps AI agents understand and interact with complex, dynamic web pages and APIs in a predictable way by embedding standard metadata directly in HTML and by exposing API documentation via a standard endpoint. This reduces reliance on brittle scraping, vision heuristics or extra middleware by making intent, interactions, prerequisites and subsequent features explicit. For API authors it offers a way to surface endpoint descriptions and input/output requirements directly to agents. For agent builders it supplies parsing tools that produce usable YAML or JSON documentation, easing integration and improving reliability of automated web and API interactions across platforms. The standard also encourages clearer semantics and better accessibility for automated clients.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

Awesome-Mind-Network

0 (0 review)
listing image

building-an-agentic-system

0 (0 review)
listing image

llm-reader

0 (0 review)
listing image

agent-sdk-go

0 (0 review)
listing image

ai-tutor-rag-system

0 (0 review)

Featured Listings

Tags

Please fill the required fields*