Agent Integration

Integrate Kite with OpenClaw, Paperclip, and other agentic orchestration platforms to give your agents real-time webhook awareness.

# Agent Integration

Kite is designed first for autonomous agents. This guide covers integrating Kite with the major agentic orchestration platforms so your agents can react to real-world events in real time.

Overview

Agents live in ephemeral environments — they don't have static IPs, they can't expose ports, and they restart often. Traditional webhooks don't work in this model. Kite bridges the gap by maintaining a persistent relay that agents connect to on demand.

OpenClaw

OpenClaw agents can subscribe to Kite event streams using the built-in sink:

Install the Kite skill

bash

kite skill install kite

This installs SKILL.md into your agent's skill directory and exports the Kite skill definition.

Stream to an OpenClaw agent

bash

kite listen --sink openclaw --source github

Events arrive in the agent's event loop as structured CloudEvent objects, ready for reasoning and action.

Export skills to agent directories

bash

kite skill export --target ~/.openclaw/skills/

Paperclip

Kite integrates natively with the Paperclip agent orchestration platform. Agents can receive webhook events as task triggers.

Install and configure

bash

kite skill install paperclip

Configure your Paperclip agent to wake on Kite events by adding an event source to the agent's adapter config:

json

{
  "kiteEventSource": "github",
  "kiteEventTypes": ["com.github.push", "com.github.pull_request.opened"]
}

How it works

1. A GitHub webhook fires on a push event 2. Kite relays it as a CloudEvent to the Paperclip bridge 3. The bridge creates or updates a Paperclip task with the event payload 4. Your agent wakes, reads the task, and takes action

Event payload in task context

The CloudEvent is available in the task's context under kiteEvent:

json

{
  "kiteEvent": {
    "type": "com.github.push",
    "source": "https://api.github.com",
    "data": { }
  }
}

MCP (Model Context Protocol)

Kite exposes a Model Context Protocol server that language models can query directly. Use it to subscribe an LLM to live webhook streams:

bash

kite mcp serve --source github

The MCP server exposes tools that models can call to stream, filter, and acknowledge events.

Generic HTTP agents

Any agent that can make HTTP requests can consume Kite events via the proxy sink:

bash

kite proxy --target http://localhost:9000/events

The agent polls or listens on port 9000. Each incoming request is a single CloudEvent with full metadata headers.

Persistent cursor tracking

For agents that restart frequently, set a --client-id so Kite replays missed events on reconnect:

bash

kite stream --source github --client-id "my-agent-prod"

Kite tracks the delivery cursor server-side per client ID, ensuring at-least-once delivery even across agent restarts.

Dead letter queue for agents

If your agent fails to acknowledge an event (crashes, times out, returns non-2xx), the event lands in Kite's local dead letter queue. Replay it when the agent recovers:

bash

kite retry --target http://localhost:9000/events