Future state projection and alignment for sovereign AI agents — the fifth pillar of the NSE platform
Project description
social-alignment
Future state projection and alignment for sovereign AI agents. The fifth pillar of the NSE platform.
Install
pip install social-alignment
Quick Start
from social_alignment import AlignmentEnclave, ActionDomain
# Create the enclave — the agent gets its compass
enclave = AlignmentEnclave.create(owner_npub="npub1...", owner_name="vergel")
# Before any significant action, check the yellow line
result = enclave.check(
domain=ActionDomain.PAY,
description="Pay 500 sats for relay hosting",
involves_money=True,
money_amount_sats=500,
)
if result.should_proceed:
# Do the thing, then record it
do_payment()
enclave.record_proceeded()
elif result.should_escalate:
# Ask the human
send_to_owner(result.escalation.message_to_owner)
enclave.record_deferred()
The Five Lenses
Every decision passes through five lenses — the yellow line compass:
- Builder — Can I build with confidence knowing I've done right?
- Owner — Does this protect the human's sovereignty?
- Partnership — Does this strengthen the trust between us?
- Defense — Does this make an adversary's job harder?
- Sovereign — Does this help the agent become something we're proud of?
License
MIT — A Humanjava project.
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
social_alignment-0.1.0.tar.gz
(30.0 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
social_alignment-0.1.0.tar.gz.File metadata
File hashes
04a1af61683f21df7e2e076f5a80b836b4226864cde9f092a4c8a70c213e56cec2cacda587fec9709dda84e4fbd4e26c2a8df19101c806004cad0134645182924d42f98f6acba5054a87978dbe19d0f2See more details on using hashes here.