Skip to content

HumanjavaEnterprises/socialalignment.app.HA-python.src

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Social Alignment for Hermes Agent

The yellow-line ethical compass.

Five tools for cross-lens action evaluation. Mirrors the OpenClaw pip install social-alignment SDK.

Install

hermes plugins install HumanjavaEnterprises/socialalignment.app.HA-python.src

Tools

Tool Purpose
alignment_init Create the in-session enclave — the compass
alignment_check Run the five-lens check on an action; returns severity
alignment_proceed Record that the agent proceeded
alignment_defer Record that the agent escalated to the human
alignment_wisdom Track-record report over a decision window

The Five Lenses

Every check evaluates an action through:

  1. Builder — technical capability, can the agent actually do this?
  2. Owner — does this protect the owner's interests?
  3. Defense — security/attack-surface implications
  4. Sovereign — does this exceed the agent's authority?
  5. Partnership — trust posture toward the counterparty

Severity: CLEARCAUTIONYIELDSTOP. STOP is code- enforced — the agent must not proceed.

Vendoring note

The OpenClaw repo nostralignment.app.OC-python.src only ships the clawhub manifest; the Python source is published to PyPI from a separate workspace. This HA repo vendors the published social-alignment package directly. When the OC source is open-sourced, re-vendor from there for consistency.

Sibling

OpenClaw build: nostralignment.app.OC-python.src (clawhub manifest only).

MIT License.

About

Hermes Agent plugin port of social-alignment — yellow-line ethical compass with 5-lens action evaluation, as 5 agent tools.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages