AIGP-Light: Minimal detect & respond governance for AI model calls — zero dependencies, RFC-010 compatible traces
Project description
maigp-light
Minimal detect & respond governance for AI model calls.
Zero dependencies. Five minutes to integrate. Forward-compatible with the full AIGP/MAIGP protocol.
Install
pip install maigp-light
Quick Start
from aigp_light import AigpLight
gov = AigpLight.from_yaml("aigp-light.yaml")
# Wrap any model call
response = gov.call(
client.chat.completions.create,
model="gpt-4o",
messages=[{"role": "user", "content": "Hello"}]
)
What It Does
- Detects behavioral deviation: latency spikes, error rates, refusal patterns, token explosions, cost overruns
- Responds automatically: LOG, ALERT, RATE_LIMIT, FALLBACK, BLOCK, CIRCUIT_BREAK
- Traces every call in RFC-010 §5.3 format (forward-compatible with full AIGP)
What It Doesn't Need
No external services. No governance server. No delegation tokens. No consent providers. No network calls. Everything runs locally from a YAML policy file.
Documentation
Upgrade Path
maigp-light → maigp-agent-core → maigp-client (full protocol)
Your traces carry forward. Your trust history accumulates from day one.
License
Source Available — free to use, no modification without permission. See LICENSE.md.
© 2024-2026 Causum. All rights reserved.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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 maigp_light-1.0.0.tar.gz.
File metadata
- Download URL: maigp_light-1.0.0.tar.gz
- Upload date:
- Size: 15.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fe83e0d7ffe74dfa2d754a1947cf08675672ce6fe0fba04bc9eeba172b45c0cb
|
|
| MD5 |
751657fa3e2b5e6ef5b54c5ee15cdf19
|
|
| BLAKE2b-256 |
d49c36e861ceb5976b08af3aad8e682bb8fea4f3d7758e1f2954482025d5555b
|
File details
Details for the file maigp_light-1.0.0-py3-none-any.whl.
File metadata
- Download URL: maigp_light-1.0.0-py3-none-any.whl
- Upload date:
- Size: 18.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
07ef21ae58b8cd5db39a0ec94dac683504668fb39a2e790bf96f46b469c9787b
|
|
| MD5 |
dc6ad47f8baa8110ad18a95c1bd36ec1
|
|
| BLAKE2b-256 |
b435df1313a82d80c69320f3c8ba0270739d267b15f72daad515886dd0363c2a
|