Skip to main content

Multi-model council orchestration with CLI and integration bridge

Project description

ai-decision-council

ai-decision-council is a plug-and-play Python SDK for multi-model council workflows:

  1. Collect first-pass answers from multiple models.
  2. Run peer ranking across those answers.
  3. Synthesize one final decision-style response.

Default behavior uses a curated set of 5 models (configurable from 2 to 20).

Install

pip install ai-decision-council

5-minute startup

# Use your OpenRouter API key here.
export LLM_COUNCIL_API_KEY="..."
ai-decision-council doctor
ai-decision-council run --prompt "Explain CAP theorem in simple terms"

5-minute API integration

pip install "ai-decision-council[api]"
export LLM_COUNCIL_API_KEY="..."
export LLM_COUNCIL_REFERENCE_API_TOKEN="replace-with-long-random-token"
ai-decision-council api serve

Then call POST /v1/conversations on http://localhost:8001.

Python integration

from ai_decision_council import Council

council = Council.from_env()
result = council.run_sync("Summarize vector databases in 5 bullets")
print(result.final_response)

CLI

ai-decision-council doctor
ai-decision-council models --defaults
ai-decision-council models --defaults --count 7
ai-decision-council init
ai-decision-council init --api fastapi
ai-decision-council api bootstrap --path .
ai-decision-council api openapi --output ./openapi.json
ai-decision-council api sdk --output-dir ./sdk
ai-decision-council run --prompt "Your prompt" --json

Legacy alias remains supported:

llm-council ...

Core configuration

  • LLM_COUNCIL_API_KEY (preferred; your OpenRouter API key)
  • LLM_COUNCIL_MODELS (explicit model list)
  • LLM_COUNCIL_MODEL_COUNT (default 5)
  • LLM_COUNCIL_CHAIRMAN_MODEL
  • LLM_COUNCIL_TITLE_MODEL
  • LLM_COUNCIL_API_URL
  • LLM_COUNCIL_REFERENCE_API_TOKEN (required for packaged API auth)

Current provider scope is OpenRouter-first. Fallback key support: OPENROUTER_API_KEY.

Documentation

  • docs/quickstart.md
  • docs/python-integration.md
  • docs/cli-usage.md
  • docs/framework-snippets.md
  • docs/troubleshooting.md
  • docs/migration.md
  • docs/openapi.json

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

ai_decision_council-1.4.0.tar.gz (74.6 kB view details)

Uploaded Source

Built Distribution

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

ai_decision_council-1.4.0-py3-none-any.whl (54.6 kB view details)

Uploaded Python 3

File details

Details for the file ai_decision_council-1.4.0.tar.gz.

File metadata

  • Download URL: ai_decision_council-1.4.0.tar.gz
  • Upload date:
  • Size: 74.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.6

File hashes

Hashes for ai_decision_council-1.4.0.tar.gz
Algorithm Hash digest
SHA256 6bc6c6a8c78ed2fdbfcd4b984187846ef2993eaac6a77fb9ed590cffb7a070b9
MD5 3c885653fa7f2ed54440f77391175283
BLAKE2b-256 eff53d714d0971ebbd17d7154b96bb24ffb21b776ab15a9cb7de46d9365e242d

See more details on using hashes here.

File details

Details for the file ai_decision_council-1.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ai_decision_council-1.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9fe71f80380657848b5506bd1c669ffb34245a0978e8260dc6983f8cdc105cf5
MD5 21e1e8ba83dfe95fd0f8038e5833bbd8
BLAKE2b-256 0cd3fee536349f55440c187c1980b1035463588aea1cf9b0973c100af939128b

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