Skip to main content
ZNYX AI

Integrate

Two calls around your model. That is the integration.

ZNYX sits beside your stack rather than inside it. Whatever model, framework, or gateway you run, the contract is the same, and it is cloud- and model-neutral by design.

Two calls around your model

Screen the input, call your model, screen the response. The 4-tuple (tenant, app, agent, env) resolves which policy applies, so no policy id travels with the call.

scope = dict(
    tenant_id=ORG,
    app_id=PROJECT,
    agent_id="triage",
    env="production",
)

inp = guardrails.evaluate_input(
    prompt, **scope
)
if inp.is_blocked:
    return inp.user_message

prompt = inp.sanitized_text or prompt
answer = llm.complete(prompt)

out = guardrails.evaluate_output(
    answer, **scope
)
return out.sanitized_text or answer

Streaming

Post response chunks and the engine evaluates a rolling window (200 chars, 40 overlap by default), streaming verdicts back over SSE. Treat a block event as terminal. Streaming is on the async client, and the stream resolves its policy from the bundle rather than the call.

stream = guardrails.evaluate_stream(
    chunks=chunks
)
async for ev in stream:
    if ev.event == "block":
        break
    if ev.event == "chunk":
        yield ev.data["text"]

Tool-call gating

Gate a tool call before it executes, from whatever hook your framework already gives you. Plan, step, retrieval, and memory writes follow the same pattern against their own endpoints.

res = guardrails.evaluate_tool(
    tool_name, tool_args, **scope
)
if res.is_blocked:
    raise ToolBlocked(
        res.user_message
    )
tool_args = (
    res.sanitized_tool_args
    or tool_args
)

Ecosystem

What it plugs into

SDKs

  • Python
  • TypeScript / Node
  • Java
  • C#
  • Ruby
  • Rust

Agent frameworks

  • LangChain
  • LlamaIndex
  • CrewAI
  • AutoGen
  • Semantic Kernel
  • Vercel AI SDK

Model providers

  • OpenAI
  • Anthropic
  • Azure OpenAI
  • Bedrock
  • Vertex AI
  • Open-weights / vLLM

Gateways & proxies

  • Envoy
  • NGINX
  • Kong
  • LiteLLM
  • Cloudflare Workers
  • API Gateway

Observability

  • OpenTelemetry
  • Prometheus
  • Webhook events
  • Datadog
  • Grafana
  • Splunk

Identity

  • Okta
  • Entra ID
  • Auth0
  • Google Workspace
  • SAML 2.0
  • SCIM 2.0

Anything that can make an HTTP call can use ZNYX. The named integrations reach these endpoints through their own framework hooks, callbacks, or middleware, and the contract is the same in every case.

FAQ

Integration questions

Where ZNYX sits in your stack, what it costs in latency, and how it fails.

Around your model call. You evaluate the input before it reaches the model, and the output before it reaches the user, with additional check points for retrieved context, tool calls, agent plans, agent steps, and memory writes if you are running agents. Nothing needs to proxy your model provider.

Secure every prompt, agent, and tool call, in your boundary.

Pull the open-source runtime, drop it into your stack, and start enforcing policy in minutes, free, forever. Add the hosted control plane when you want centralized policies, evidence, traces, and team workflows.