Skip to main content

Neuronto - Agentic Resource Discovery (ARD) Index

Alias package. This installs ard-publish and re-exports it, so the tool is installable under the full term as well as the short one.

pip install agentic-resource-discovery      # this package
pip install ard-publish                     # identical, shorter to type

Both give you the same module and the same CLI.

What it does

Build, validate and verify an Agentic Resource Discovery (ARD) manifest — the /.well-known/ard.json file that lets AI agents find your API, MCP server or agent at runtime, without anyone installing it in advance.

from agentic_resource_discovery import Manifest, Entry

m = Manifest(host="example.com", display_name="Example Inc")
m.add(Entry.mcp_server(
    name="weather", display_name="Weather API", host="example.com",
    url="https://example.com/.well-known/mcp/server-card.json",
    description="Current conditions and forecasts for any location.",
    queries=["what is the weather in Berlin", "will it rain in London tomorrow"],
))
m.save(".well-known/ard.json")
ard-publish check example.com     # which registries actually return you

What is ARD?

ARD stands for Agentic Resource Discovery: the open specification for how AI agents find the tools, skills, agents and APIs they need, published in June 2026 by a working group including Google, Microsoft, Hugging Face, AWS, Cisco, GitHub, Nvidia, Salesforce and Snowflake.

Full documentation lives on the main package: pypi.org/project/ard-publish

Licence

Apache-2.0

Metadata

Release files for agentic-resource-discovery 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentic-resource-discovery 1.0.1
File Size Uploaded
agentic_resource_discovery-1.0.1.tar.gz 7.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for agentic-resource-discovery 1.0.1
File Interpreter ABI Platform
agentic_resource_discovery-1.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 14.8 kB

Release files / agentic_resource_discovery-1.0.1.tar.gz

Download URL agentic_resource_discovery-1.0.1.tar.gz
Size 7.0 kB
Tags Source
SHA-256 checksum
How to use checksums
cb941184e8a8213b0599c1e8e0469c080ad45ce4aed037afe6a8363f3ee41530
BLAKE2b-256 checksum
How to use checksums
ca56a2cd8772e16813ee9f4c6f8ae0e2cf1063e2cd648b81150e3c95d978eaf3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Release files / agentic_resource_discovery-1.0.1-py3-none-any.whl

Download URL agentic_resource_discovery-1.0.1-py3-none-any.whl
Size 7.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c494188aa3a6fdcebebde9cb1cf512f4c19aa9791c047887f4f134e7fedfdcf1
BLAKE2b-256 checksum
How to use checksums
623863276d40bfe7d54f4e3165b2bed6f1786d9b9f1e9a908be8bb2819ac4151
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page