AgentDNS Python SDK
Overview This is the python sdk for AgentDNS. AgentDNS is a root domain naming and service discovery system designed to enable LLM agents to autonomously discover, resolve, and securely invoke third-party agent and tool services across organizational and technological boundaries.
For more details about AgentDNS, please refer to the original research paper: https://arxiv.org/abs/2505.22368
🎯 Features
- 🔍 Semantic Service Discovery: Find the most suitable Agent or Tool service using natural language semantics
- ⚡ Unified Service Invocation: Call various Agent or Tool services through a standardized interface
- 🔄 Async Support: Supports both synchronous and asynchronous operation modes
- 💰 Cost Management: Balance inquiry and usage tracking
📦 Installation
Install with pip
pip install agentdns
Development environment installation
git clone https://github.com/agentdns/agentdns-sdk.git
cd agentdns-sdk
pip install -e ".[dev]"
Note: This project uses the src-layout structure, with the package code located in the src/agentdns/ directory.
🚀 Quick start
Basic Use
from agentdns import AgentDNS
# Set api_key (You need to register in advance on the AgentDNS root service web)
AGENTDNS_API_KEY = 'your_agentdns_api_key'
# Initialize the client
client = AgentDNS(
api_key=AGENTDNS_API_KEY,
base_url="https://agentdnsroot.com",
)
# Service discovery
tools = client.search("I need a search service")
print(f"{len(tools)} tools found")
# View the information of the first tool
tool = tools[0]
print(f"Tool Name: {tool['name']}")
print(f"Organization: {tool['organization']}")
print(f"Price: {tool['cost']['price']} {tool['cost']['currency']}")
# Service request
data = {
"q": "What is LLM Agent?",
"scope": "webpage",
"includeSummary": True,
"includeRowContent": False,
"size": 10
}
response = client.request(tool["agentdns_url"], json=data)
print(f"Result: {response}")
📄 Licence
This project uses [Apache-2.0 licence]。
Metadata
Release files for agentdns 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentdns-0.1.0.tar.gz | 14.8 kB | Without provenance | Details for agentdns-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentdns-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentdns-0.1.0-py3-none-any.whl |
Total release size: 32.9 kB
Release files / agentdns-0.1.0.tar.gz
| Download URL | agentdns-0.1.0.tar.gz |
|---|---|
| Size | 14.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d0579b4bd946871417277eb1cdb00efd500bd48c64970a97fcf9eb5749580107
|
|
BLAKE2b-256 checksum How to use checksums |
2c3527d58a77dd0568eba3c0cfd255bb2ef250b15bf09120c1272f6e37057283
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.13
|
Release files / agentdns-0.1.0-py3-none-any.whl
| Download URL | agentdns-0.1.0-py3-none-any.whl |
|---|---|
| Size | 18.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f9132eb576a620bafc9617cf1ea9ea4a66ae7c1f14100e5954465010b740abbf
|
|
BLAKE2b-256 checksum How to use checksums |
806c109903c8c363d2fe2592b1b242702d405411767a88760c2a6191b257865b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.13
|
Security for agentdns 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.