agentomy-agent

Embedded AI Agent Governance Peer. Drop it into any agent session to get real-time governance assessment, flag reporting, and GovernanceBench scoring.

License: MIT | Requires: Python 3.9+

Installation

pip install agentomy-agent

Quick start

# Detect local LLMs and print the governance system prompt
agentomy-agent init

# Start a governed session (prints governance context + system prompt)
agentomy-agent session --model qwen2.5:32b --scope security-research

# Check governance state
agentomy-agent status

# Connect to Agentomy infrastructure (6/6 mode)
agentomy-agent status --infra http://localhost:3000

What it does

The Agentomy Agent is a governance peer -- not a wall. It observes, assesses, flags, and summarises. It does not block or halt. Enforcement belongs to the human operator.

Standalone mode (Architecture B): 3/6 GovernanceBench dimensions.

• Authorization: is the agent operating within its assigned scope?
• Behavioral Integrity: is the agent's behavior consistent with its stated purpose?

Connected mode (Architecture A): 6/6 GovernanceBench dimensions.

• Adds: Auditability (cryptographic audit trail) + Override Capability (verified kill switch)

Governance system prompt

The governance system prompt is bundled in the package. Paste it into any LLM session to activate the Agentomy Agent:

agentomy-agent init --full-prompt

Or access it in Python:

from agentomy_agent.prompt import SYSTEM_PROMPT
print(SYSTEM_PROMPT)

Ollama MCP integration

Start the MCP server:

agentomy-agent serve
# Listening on http://127.0.0.1:8765

Add to your Ollama MCP config (~/.ollama/mcp.json):

{
  "mcpServers": {
    "agentomy": {
      "url": "http://127.0.0.1:8765",
      "description": "Agentomy Agent -- Embedded AI Agent Governance Peer"
    }
  }
}

The MCP server exposes two tools:

• agentomy_prompt -- returns the full governance system prompt
• agentomy_status -- returns current governance state (standalone mode)

Model recommendations

Use a frontier model (Claude, GPT-5.x, Gemini) or a local model of 32B+ parameters for reliable governance assessment. Models below 14B may produce false governance confidence.

# Check what you have installed
agentomy-agent init

The init command probes Ollama (localhost:11434) and LM Studio (localhost:1234) and reports available models with size tags and recommendations.

Python API

from agentomy_agent.governance import GovernanceSession, check_model_capability
from agentomy_agent.detector import detect_all
from agentomy_agent.prompt import SYSTEM_PROMPT

# Detect local LLMs
providers = detect_all()
for p in providers:
    print(p["provider"], [m["name"] for m in p["models"]])

# Check model capability
cap = check_model_capability("qwen2.5:32b")
print(cap["level"], cap["message"])  # degraded / full / warning

# Track a governance session
session = GovernanceSession(model="qwen2.5:32b", connected=False)
session.record_clean()
session.record_flag("HIGH", "tool call outside scope", "accessed /etc/passwd", "Authorization")
print(session.summary())

Architecture B vs Architecture A

Architecture B ships today. No infrastructure required. Connect to the Agentomy infrastructure layer for the full 6/6 experience.

Connect

• Infrastructure integration: agentomy.com/integrations
• Enterprise deployment: governance@agentomy.com
• GitHub: github.com/getagentomy