Ecosystem
Seven strategic products that extend the core platform — from free risk tooling and open source SDKs to certification, APIs, and insurer partnerships.
Runtime interception for AI agents. Every tool call goes through synchronous policy enforcement before execution — not after. Tamper-evident audit trail, kill switch, compliance passports. The governance layer IBM and Microsoft don't have.
npm install @rends/agent-sdkpip install rends-agent-sdkEvery client.govern() call runs through this pipeline:
npm install @rends/agent-sdk
pip install rends-agent-sdk
import { RendsClient } from "@rends/agent-sdk";
const client = new RendsClient({
apiKey: "ac_live_...",
orgId: "your-org-uuid",
agentId: "your-agent-uuid",
mode: "enforce", // or "monitor" or "dry-run"
});
const result = await client.govern(
{
actionType: "database_query",
actionName: "select_users",
resourceType: "customer_records",
inputSummary: "SELECT * FROM users WHERE region = us-east-1",
},
async (params) => db.query("SELECT * FROM users")
);
// result.allowed = true/false
// result.status = "pass" | "warn" | "block"
// result.result = query output (if allowed)
// result.check.violations = [{ruleName, message, severity}]from rends_sdk import RendsClient, RendsClientConfig, ActionContext
async with RendsClient(RendsClientConfig(
api_key="ac_live_...",
org_id="your-org-uuid",
agent_id="your-agent-uuid",
)) as client:
result = await client.govern(
ActionContext(
action_type="database_query",
action_name="select_users",
resource_type="customer_records",
input_summary="SELECT * FROM users",
),
tool_fn=lambda p: db.query("SELECT * FROM users"),
)One-line integration for every major agent framework.
TypeScript & Python
import { governTools } from "@rends/agent-sdk/adapters/langchain";
// Wrap all tools in one line
const governed = governTools(client, [search, calculator, browser]);
const agent = createReactAgent({ llm, tools: governed });Python
from rends_sdk.adapters import govern_crewai_tool search = SerperDevTool() governed = govern_crewai_tool(client, search, resource_type="web_search") agent = Agent(tools=[governed], ...)
Python
from rends_sdk.adapters import govern_autogen_tool
governed_search = govern_autogen_tool(
client, search_web, "search_web", resource_type="web_search"
)
agent.register_function(function_map={"search_web": governed_search})BLOCK → throws GovernanceBlockError. Tool never executes.
All decisions logged but never block. Full telemetry, zero disruption.
Policy checked, nothing executed. Test rules before deployment.