Big News: Socket raises $60M Series C at a $1B valuation to secure software supply chains for AI-driven development.Announcement
Sign In

@superinstance/agent-field

Package Overview
Dependencies
Maintainers
1
Versions
1
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@superinstance/agent-field

Shared tensor field for within-agent room coordination with 9-channel semantics

latest
npmnpm
Version
0.1.0
Version published
Maintainers
1
Created
Source

agent-field

Shared tensor field for within-agent room coordination.

9-channel semantics: confidence, entropy, drift, focus, gap, salience, coupling, resonance, phase.

Rooms are views into a shared tensor. Coupling is a matrix. Gaps self-organize.

Installation

pip install agent-field

Standalone — no hard dependencies. Optionally integrates with flux-tensor-midi for FluxVector/TZeroClock support.

Quick Start

from agent_field import AgentField

field = AgentField()
sensor = field.add_room("drift-sensor", role="sensor")
predictor = field.add_room("drift-predict", role="predictor")
field.couple(predictor, sensor, strength=0.9)

field.sensor_write(sensor, [0.8, 0.2, 0.01, 0.9, 0.0, 1.0, 0.0, 0.0, 0.0])
field.tick()

print(field.focus_queue())
print(field.field_report())

License

MIT

FAQs

Package last updated on 21 May 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts