SAWANT Agentic MoSCoW Framework for Reliable LLM Outputs
Project description
SAMF: SAWANT Agentic MoSCoW Framework
Structural MoSCoW contracts for deterministic LLM validation.
What is it?
SAMF provides machine-readable validation contracts for LLMs, translating project management MoSCoW prioritization into strict alignment guards.
Why do I need it?
- Slashes Prompt Instability: Eliminates brittle multi-hop reasoning.
- Prevents Loop Breaches: Keeps multi-agent reasoning loops from breaking.
- Optimizes Token Costs: Reduces RAG token waste by enforcing explicit constraints.
Quick Start
from samf import SAMFContract, samf_contract
# Define your strict execution contract
guard_contract = SAMFContract(
must_have=["JSON", "status", "user_id"],
should_have=["timestamp"],
wont_have=["error", "failed"]
)
# Enforce it seamlessly with a decorator
@samf_contract(contract=guard_contract)
def call_billing_agent():
# Your LLM generation / LangGraph node logic here
return '{"status": "success", "user_id": 4002, "format": "JSON"}'
response = call_billing_agent()
print("Output validated successfully!")
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
samf_framework-0.1.3.tar.gz
(2.9 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 samf_framework-0.1.3.tar.gz.
File metadata
- Download URL: samf_framework-0.1.3.tar.gz
- Upload date:
- Size: 2.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
55eaabb2889841f69eab843b0e80d2da6837c0895ded62fda71c3f57dc755938
|
|
| MD5 |
19c0754b2247469261144c32fbf2a1f5
|
|
| BLAKE2b-256 |
5af42c17a9f494abda87442bccadbd577055bd965827728f0fda01cb62f0a20a
|
File details
Details for the file samf_framework-0.1.3-py3-none-any.whl.
File metadata
- Download URL: samf_framework-0.1.3-py3-none-any.whl
- Upload date:
- Size: 3.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8b1938aa131d685f68a24e66f7ea6eebc9432772ccbf3c23f5116620b0352825
|
|
| MD5 |
76d7d98dae9b44b497a5047eda96ab4b
|
|
| BLAKE2b-256 |
eb79f5819ef5bc4ac46b30ab786977b4d6acf72e0a9e53da049e5a496053e59b
|