majordomo-frameworks
Framework adapters for routing LLM requests through Majordomo Gateway with centralized logging and cost tracking.
Installation
# Core package (no framework dependencies)
pip install majordomo-frameworks
# With Agno support
pip install majordomo-frameworks[agno]
# With Pydantic AI support
pip install majordomo-frameworks[pydantic-ai]
Quick Start
Shared utilities (zero dependencies)
from majordomo_frameworks import build_headers, check_environment, Provider
# Check required env vars are set
missing = check_environment("openai")
# Build gateway headers
headers = build_headers(feature="my-feature", step="inference", user_id="alice")
Agno
from majordomo_frameworks.agno import create_model
model = create_model("openai", feature="support-agent", user_id="alice")
Pydantic AI
from majordomo_frameworks.pydantic_ai import create_model, build_extra_headers
from pydantic_ai.settings import AnthropicModelSettings
# Create model routed through the gateway
model = create_model("anthropic")
# Build headers for model settings
headers = build_extra_headers(feature="research-agent", step="synthesis")
# Use with Pydantic AI model settings
settings = AnthropicModelSettings(
extra_headers=headers,
# ... other settings like anthropic_thinking, etc.
)
Supported Providers
| Provider | Agno | Pydantic AI |
|---|---|---|
| OpenAI | OpenAIChat |
OpenAIModel |
| Anthropic | OpenAILike |
AnthropicModel |
| Gemini | OpenAILike |
OpenAIModel |
Environment Variables
| Variable | Required | Description |
|---|---|---|
MAJORDOMO_GATEWAY_URL |
No | Gateway URL (default: http://localhost:7680) |
MAJORDOMO_API_KEY |
Yes | Your Majordomo API key |
OPENAI_API_KEY |
Per provider | OpenAI API key |
ANTHROPIC_API_KEY |
Per provider | Anthropic API key |
GEMINI_API_KEY |
Per provider | Gemini API key |
Documentation
- Pydantic AI Guide - Complete guide with migration instructions, advanced usage, and examples
Examples
- Agno Support Agent - Multi-turn conversations with per-user cost tracking
- Pydantic AI Research Agent - Multi-step research workflow with structured outputs
License
MIT
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
majordomo_frameworks-0.2.0.tar.gz
(343.6 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file majordomo_frameworks-0.2.0.tar.gz.
File metadata
- Download URL: majordomo_frameworks-0.2.0.tar.gz
- Upload date:
- Size: 343.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb1b2f3442529deeab0afa85849277101df4eb1d3f44d99b6b5dce2a86b7f1b1
|
|
| MD5 |
b89afabccfee8f0b428f602113a2bdc5
|
|
| BLAKE2b-256 |
655c95ce96f755414304083bbd117fbc039268e9575e18484555e80882499736
|
File details
Details for the file majordomo_frameworks-0.2.0-py3-none-any.whl.
File metadata
- Download URL: majordomo_frameworks-0.2.0-py3-none-any.whl
- Upload date:
- Size: 7.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
aed7baba1d50ede7c6f7ac95f1e6d4b804a0ecb06033a309e4dab6022b0a4e21
|
|
| MD5 |
1c94857433de3cc91593c38108ef3198
|
|
| BLAKE2b-256 |
42c746fa11e821c4483cc4afce4c0f4366c1f9475691c2bd5c364ea2dcc97951
|