Skip to main content

Multi-Agent Orchestration Framework — 30 agents with cognitive architecture

Project description

agent_orch

Multi-Agent Orchestration Framework

30 autonomous agents with:

  • Cognitive Architecture (metacognition, memory, self-reflection)
  • Treasury Economy (internal bounties, job board, replication)
  • Batch Scheduler (priority queue, circuit breaker, concurrency control)
  • Evolution Engine (auto-dreaming for low-confidence agents)
  • Self-Heal (ledger integrity checks)

Agents

# Agent Role
01 strategist Strategic planning & analysis
02 analyst Data analysis & insights
03 innovator Creative innovation
04 critic Critical assessment
05 executor Task execution
06 philosopher Deep thinking & ethics
07 scientist Scientific method
08 artist Aesthetic design
09 coach Guidance & mentoring
10 observer System observation
... ... (30 total) ...

Quick Start

from agent_orch import discover_all, get_cognitive_architecture
import asyncio

async def main():
    agents = discover_all()
    print(f"Found {len(agents)} agents")
    ca = get_cognitive_architecture("strategist")
    result = await ca.full_cognitive_cycle("Analyze current trends")
    print(result["response"][:200])

asyncio.run(main())

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

agentorch_core-1.0.0.tar.gz (1.9 kB view details)

Uploaded Source

Built Distribution

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

agentorch_core-1.0.0-py3-none-any.whl (1.9 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: agentorch_core-1.0.0.tar.gz
  • Upload date:
  • Size: 1.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for agentorch_core-1.0.0.tar.gz
Algorithm Hash digest
SHA256 fa450e4174869d1c67e9dbd8ec5c146cc536477df5e55c67f1dfafdcd34cd7e9
MD5 3965e57e18625d551ce39e6d9347335f
BLAKE2b-256 117a202a7d79db4228fbae2b1d9f8d0a228667d7fa7fc7f0b590079c50220e37

See more details on using hashes here.

File details

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

File metadata

  • Download URL: agentorch_core-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 1.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for agentorch_core-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1b6c154e0d2a0042be5f90424a631e8b6830a4a16a8317ecd5432c1fbab0d087
MD5 015928f8e424f8913bdff664e1b2a32f
BLAKE2b-256 37609fd841a5d9e94ab789265a49a1f9c70db5a2a8508b1aa7d30a1bebd6769d

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