Two runtimes. One verdict.

Node

The common pattern is guard.wrap: put the decision in front of the function you want governed, and leave the function itself alone.

import { guard } from "@cirvix_ai/agent-control";

const readFile = guard.wrap(
  { action: "read:file", agent_id: "agent-01" },
  async (path) => fs.readFile(path, "utf8")
);

// Denied calls throw before the body runs.
// The decision is recorded either way.
await readFile(".env");  // CirvixDenied: deny-dotenv-read

The gateway and the SDK share one decision core, so wrapping a call locally and routing it through the gateway produce the same verdict for the same request.

Python

The Python package (cirvix on PyPI) ships a native evaluator rather than a thin HTTP client, so local policy decisions require no round trip.

from cirvix import guard, CirvixDenied, CirvixHeld, STARTER_RULES

def read_file(args):
    return open(args["path"]).read()

# Wrap a tool map, sequence of LangChain/CrewAI tools, or single callable
tools = guard.wrap(
    {"read_file": read_file},
    agent="agent-01",
    rules=STARTER_RULES,
)

try:
    tools["read_file"]({"path": ".env.production"})
except CirvixDenied as err:
    print(err.policy)       # "deny-dotenv-read"
    print(err.decision_id)  # "dec_..."

SDK Capability Matrix: Node.js vs. Python

Both SDKs share the canonical policy evaluator for covered inputs, but runtime capabilities differ fundamentally. Capabilities of one runtime must not be assumed in the other.

Pre-built Ecosystem Plugins (10-Second Setup)

Drop Cirvix governance into leading developer tooling and multi-agent frameworks with zero architectural overhaul.

# Auto-registers into Claude Code MCP registry
claude mcp add cirvix -- cirvix gateway --strict

// .vscode/settings.json
{
  "cirvix.daemon.autoStart": true,
  "cirvix.enforcePolicies": "strict",
  "cirvix.ipcSocket": "unix:///var/run/cirvix/ipc.sock"
}

from cirvix import Guard

# 1-line wrap for LangChain, LlamaIndex, or CrewAI agents
agent = Guard.wrap(raw_agent, agent_id="autonomous-analyst")

Framework Examples

from cirvix import Guard
from crewai import Agent, Crew, Task
from langchain.agents import create_openai_tools_agent

# 1. Wrap LangChain Agent
langchain_agent = create_openai_tools_agent(llm, tools, prompt)
governed_agent = Guard.wrap(langchain_agent, agent_id="triage-agent")

# 2. Wrap CrewAI Crew
crew = Crew(agents=[dev_agent], tasks=[refactor_task])
governed_crew = Guard.wrap(crew, agent_id="dev-crew")

# Any tool invocation that violates policy throws CirvixDenied
# and records a hash-chained (unsigned) entry in the audit log.

Why a shared fixture

Two implementations of the same rule language will drift. The conformance fixture is the thing that stops that: a corpus of requests and expected verdicts that both engines must reproduce exactly.

It earns its keep. When the fixture was first run across both engines it immediately surfaced a real path-canonicalization difference on Windows — a case where the two evaluators would have disagreed about whether a resource matched.

Not available

There is no Go, Java, or Ruby SDK today. If your runtime is not Node or Python, use the HTTP gateway or the Node runtime daemon / gateway — it is the same decision core behind a network boundary. We would rather say this plainly than list a language we have not built.