---
title: "AgentSDK: Build Production AI Agents on Telnyx Edge Compute"
canonical: https://telnyx.com/products/agentsdk
---
# AgentSDK: Build Production AI Agents on Telnyx Edge Compute

# AgentSDK

Durable state, zero-hop platform bindings, your framework unchanged.

[Start Building](https://telnyx.com/sign-up)[Read the Docs](https://developers.telnyx.com)

WHY TELNYX

## The agent SDK with the network underneath

Every other agent stack has a seam. Your agent runs on a compute platform, its memory lives in a database, its LLM calls go to an inference provider, its phone calls go through a telephony API. AgentSDK closes the seam.

* ### One API key, one bill  
Inference, voice, messaging, KV, and storage all through the same API key. No multi-vendor setup, no separate billing, no integration glue between services.
* ### Models in the same facility as your code  
Your agent runs on Edge Compute in the same datacenter as inference GPUs. No cross-region hop to a cloud provider endpoint, no network latency between your logic and your model.
* ### Carrier-owned network underneath  
Voice and messaging run on Telnyx own network, not a third-party telephony API. Your agent phone calls never leave the platform.

FEATURES

## What your framework is missing

Three primitives for durable state. Platform bindings to voice, messaging, inference, and storage. No credentials, no network calls.

* Persistent message history  
Every message stored in a structured table. Query by role and time. Your agent remembers context across sessions without external infrastructure.
* Durable scheduled tasks  
Timers that survive restarts. Schedule follow-ups, queue background work, and trust that tasks execute even after deploys.
* Merge-patch state  
Durable state on a single KV key. Concurrent updates merge, they dont clobber. No race conditions, no lost state.
* Inference (via telnyx binding)  
Call models on owned GPUs through the telnyx binding. OpenAI-compatible. Same facility as your agent code, no network hop. Accessed via this.env.TELNYX.ai.
* Voice and messaging bindings  
Make and take real phone calls. Send and receive SMS, MMS, and WhatsApp. Carrier infrastructure, not a third-party telephony API.
* Storage bindings  
KV and Cloud Storage through platform bindings. Zero-credential access from your agent code. Accessed via this.env.

GET STARTED

## Subclass Agent. Bring your framework. Deploy.

One class. Three primitives. Zero-hop bindings.

[EXPLORE DEV DOCS](https://developers.telnyx.com)

TypeScript

```
import { Agent } from "@telnyx/edge-runtime";

class SupportAgent extends Agent {
  async onMessage(msg) {
    const res = await this.env.TELNYX.ai.openai.chat.createCompletion({
      model: "glm-5.2",
      messages: [...await this.messages.list(), msg],
    });
    await this.env.TELNYX.messages.send({
      to: msg.from, from: msg.to, text: res.choices[0].message.content,
    });
    await this.schedule("follow-up", 86400);
  }
}
```

PRODUCTS

## One runtime. Every platform primitive your agent needs.

AgentSDK runs on Edge Compute. These are the platform primitives your agent can reach without leaving the network.

[See all products](https://telnyx.com/products)

* [![Telnyx Edge Compute platform flow comparison](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/Pillar-Flow-Comparison_Physics-Edge-Compute_16x9.png?width=2560&format=webp)Edge ComputeAgentSDK runs here. Your code executes at the telecom edge, in the same facility as inference and the network.](https://telnyx.com/edge-compute)
* [![Model Library — open-source and proprietary LLMs](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/LLM_Hero_16x9%402x.webp?width=1024&format=webp)InferenceAccess GLM-5.2, Kimi K3, and MiniMax-M3 on dedicated GPUs.](https://telnyx.com/products/inference)
* [![Voice-AI-Agents_Hero](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/Voice-AI-Agents_Hero_16x9%402x.webp?width=1024&format=webp)Voice AIBuild and deploy low-latency voice AI agents.](https://telnyx.com/products/voice-ai)
* [![Stateful Actors hero](https://us-central-1.telnyxcloudstorage.com/aimarketingmaterials/statefulactor_hero---a8760bd3-f66c-428c-ab25-e2887f4990e8.png)Stateful ActorsDurable, consistent state for every entity in your application. No database to manage, no locks to write.](https://telnyx.com/products/stateful-actors)

## Bring your agents home.

Your agents code, state, storage, model calls, phone calls, and text messages, on one platform.

[SIGN UP](https://telnyx.com/sign-up)[TALK TO US](https://telnyx.com/contact-us)

## Bring your agents home.

Your agents code, state, storage, model calls, phone calls, and text messages, on one platform.

[SIGN UP](https://telnyx.com/sign-up)[TALK TO US](https://telnyx.com/contact-us)

## FAQ

### What is AgentSDK?

AgentSDK is a TypeScript base class that extends StatefulActor with three primitives: persistent message history, durable scheduled tasks, and merge-patch state. It ships inside @telnyx/edge-runtime.

### What frameworks does AgentSDK support?

### What are platform bindings?

### How is AgentSDK different from Cloudflare Agents?

### Is AgentSDK free?

### What is the current status?

### How do I get started?

[Start building](https://telnyx.com/sign-up)