Agentia: Ergonomic LLM Agents
Ergonomic LLM Agents with MCP and Skills support.
Getting Started
Run agents with tools, MCP, and Skills
from agentia import Agent, MCP
from typing import Annotated
# Define a tool as a python function
def get_weather(location: Annotated[str, "The city name"]):
"""Get the current weather in a given location"""
return { "temperature": 72 }
# Declare a MCP server:
calc = MCP(name="calculator", command="uvx", args=["mcp-server-calculator"])
# Create an agent
# This will load the function tool, the calculator MCP, and all skills under $CWD/.skills
agent = Agent(model="openai/gpt-5-nano", tools=[get_weather, calc], skills=True)
# Run the agent with the mcp
response = await agent.run("Calculate 234 ** 3")
print(response.text)
# Output: The result of 234 raised to the power of 3 is 12,812,904.
The Magic Decorator
Create agent-powered magic functions.
Support both plain types and pydantic models as input and output.
from agentia import magic
from pydantic import BaseModel
class Forcast(BaseModel):
location: str
temperature_celsius: int
@magic
async def get_weather(weather_forcast: str) -> Forcast:
"""Create weather forcase object based on the input string"""
...
forcast = await get_weather("The current temperature in Boston is 72°F")
print(forcast.location) # Output: Boston
print(forcast.temperature_celsius) # Output: 22
Supported Parameter and Result Types
- Any types that can be passed to
pydantic.TypeAdaptor:- Builtin types:
int,float,str,bool,tuple[_],list[_],dict[_, _] - Enums:
Literal['A', 'B', ...],StrEnum,IntEnum, andEnum - dataclasses
- Builtin types:
pydantic.BaseModelsubclasses
Metadata
Release files for agentia 0.1.41
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 |
|---|---|---|---|---|
| agentia-0.1.41.tar.gz | 39.8 kB | Without provenance | Details for agentia-0.1.41.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentia-0.1.41-py3-none-any.whl | Python 3 | none | any | Details for agentia-0.1.41-py3-none-any.whl |
Total release size: 92.5 kB
Release files / agentia-0.1.41.tar.gz
| Download URL | agentia-0.1.41.tar.gz |
|---|---|
| Size | 39.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
076e7fdeae30db567dcc0f5bd7ccaead5659948ee85ebfa85c256739ad26b74b
|
|
BLAKE2b-256 checksum How to use checksums |
a998dbdf1fd6f171224d4788685e0efa875004f30b7cb3d68e5a796c85702ea9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / agentia-0.1.41-py3-none-any.whl
| Download URL | agentia-0.1.41-py3-none-any.whl |
|---|---|
| Size | 52.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9f561ca5acbe1eede2fee1aa8ef2d5be48a1338d33624c108437f9a5f56676d2
|
|
BLAKE2b-256 checksum How to use checksums |
65ec0ed246be6e03755cadcfcc1832c500a6f9732c577a06255b169bf531b5ac
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for agentia 0.1.41
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.