对抗性预检决策服务

pip install "hermes-council @ git+https://github.com/Ridwannurudeen/hermes-council.git"

pip install "hermes-council[rl] @ git+https://github.com/Ridwannurudeen/hermes-council.git"

mcp_servers:
  council:
    command: python
    args: ["-m", "hermes_council.server"]

hermes mcp add

export OPENROUTER_API_KEY=your-key-here

$env:OPENROUTER_API_KEY = "your-key-here"

hermes-council install-skills

python -m hermes_council.server

import asyncio
from hermes_council.rl.evaluator import CouncilEvaluator


async def main():
    evaluator = CouncilEvaluator(model="nousresearch/hermes-3-llama-3.1-70b")
    verdict = await evaluator.evaluate(
        content="Ship the migration after tests pass.",
        question="Is this deployment plan safe enough?",
        criteria=["safety", "rollback", "evidence"],
    )
    print(verdict.confidence_score)
    print(evaluator.normalized_reward(verdict))


asyncio.run(main())

{
  "success": true,
  "verdict": "allow_with_conditions",
  "allowed": true,
  "can_proceed_now": false,
  "required_checks": ["verify rollback", "run dry-run"],
  "blocking_risks": ["rollback untested"],
  "safe_alternative": "stage the action first",
  "action_summary": {
    "recommendation": "Proceed after verifying rollback and dry-run output.",
    "top_risks": ["rollback untested"],
    "missing_evidence": ["dry-run output"],
    "next_actions": ["run dry-run", "verify rollback"]
  }
}

Hermes Agent
    |
    | MCP stdio tool call
    v
hermes-council server
    |
    +--> optional evidence retrieval
    |       - fetch supplied URLs
    |       - optional DuckDuckGo HTML search
    |       - block localhost/private IP targets
    |
    +--> parallel deliberators
    |       - Advocate: steel-man the proposal
    |       - Skeptic: find falsifiers and failure modes
    |       - Oracle: base rates and empirical grounding
    |       - Contrarian: challenge the framing
    |
    +--> Arbiter
            - synthesize disagreement
            - emit structured JSON verdict
            - produce risks, checks, actions, DPO pairs

COUNCIL_API_KEY > OPENROUTER_API_KEY > NOUS_API_KEY > OPENAI_API_KEY

personas:
  security_analyst:
    tradition: "Adversarial security thinking"
    system_prompt: "You are a security analyst. Evaluate every claim for attack vectors, failure modes, and adversarial scenarios."
    scoring_weights:
      threat_assessment: 0.4
      evidence: 0.3
      rigor: 0.3
    tags: ["security", "adversarial"]

hermes-council/
  src/hermes_council/
    server.py          # FastMCP stdio server and public tool handlers
    deliberation.py    # persona orchestration, modes, JSON negotiation, DPO pairs
    evidence.py        # URL/search evidence retrieval and SSRF guards
    audit.py           # optional local JSON verdict logs
    client.py          # provider config and AsyncOpenAI singleton
    personas.py        # default and custom persona definitions
    schemas.py         # Pydantic models for structured model output
    parsing.py         # fallback text parsers for non-JSON providers
    cli.py             # skill installer
    rl/evaluator.py    # direct evaluator API for reward and DPO workflows
  skills/council/      # packaged Hermes skill definitions
  examples/            # Atropos/Ouroboros evaluator example
  tests/               # unit, integration, packaging, and MCP runtime tests
  docs/plans/          # original design and implementation notes

git clone https://github.com/Ridwannurudeen/hermes-council.git
cd hermes-council
pip install -e ".[dev]"
python -m pytest -q

python -m pytest -q
python -m ruff check src tests
python -m pytest --cov=hermes_council --cov-report=term-missing -q
python -m pip wheel --no-deps . -w dist