Skip to main content

USD Cognitive Substrate - State engine for multi-agent AI orchestration

Project description

USD Substrate

Python state engine for the Cognitive Orchestrator platform.

Installation

pip install usd-substrate

Usage

from datetime import datetime
from usd_substrate import (
    JsonInterchangeReader,
    JsonInterchangeWriter,
    SessionState,
    ActiveMode,
    Paradigm,
    EnergyLevel,
    BurnoutLevel,
    MomentumPhase,
    AgentType,
)

# Create a session state
state = SessionState(
    session_id="my-session",
    timestamp=datetime.now().isoformat(),
    active_mode=ActiveMode.FOCUSED,
    active_paradigm=Paradigm.CORTEX,
    energy_level=EnergyLevel.MEDIUM,
    burnout_level=BurnoutLevel.GREEN,
    momentum_phase=MomentumPhase.BUILDING,
    session_start_goal="Complete the project",
)

# Write to file
writer = JsonInterchangeWriter()
doc = writer.create_session_state_document(state)
writer.write_to_file(doc, "cognitive_state.json")

# Read from file
reader = JsonInterchangeReader()
loaded = reader.read_from_file("cognitive_state.json")
session = reader.extract_session_state(loaded)

# Create a cross-agent handoff
arc_doc = writer.create_mycelium_arc(
    session_state=state,
    source_agent=AgentType.CLAUDE_CODE,
    target_agent=AgentType.GEMINI_CLI,
    resume_summary="Working on implementation",
)

Features

  • Pydantic Models: Full type validation
  • Checksum Verification: Document integrity
  • Safety Constraints: RED burnout protection
  • Cross-Agent Handoffs: Mycelium Arc protocol

License

MIT

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

usd_substrate-1.0.0.tar.gz (23.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

usd_substrate-1.0.0-py3-none-any.whl (19.1 kB view details)

Uploaded Python 3

File details

Details for the file usd_substrate-1.0.0.tar.gz.

File metadata

  • Download URL: usd_substrate-1.0.0.tar.gz
  • Upload date:
  • Size: 23.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for usd_substrate-1.0.0.tar.gz
Algorithm Hash digest
SHA256 5779e9b5b51fbeb5d577396fc0d917fb838c52a1fa265ce9a0149708f4527b1e
MD5 1ac5c0b2d300377b8be7d6cf76ed7810
BLAKE2b-256 4072f92e3228d23aa4a82b9ebc90e86e3cf7273742800e3310c068c6c360b1ee

See more details on using hashes here.

File details

Details for the file usd_substrate-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: usd_substrate-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 19.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for usd_substrate-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e0587ffe8cfa0d403b56455c91d58d19fe6b2d29d38ac3de0291bfd517fd0139
MD5 7349c24bb977bece0aca1a9eaf2ef2f4
BLAKE2b-256 364aba9330d0f64ba4dff17fc816e0b723a3a7a2def77a1d083545dca70f2bb5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page