Agents & harnesses
Define the model, instructions, and tools. Add a reusable execution environment with the harness package.
Open guideAgentium / TypeScript AI SDK
Build agents, voice conversations, image generation, and phone calls with one TypeScript SDK. Add the tools, memory, workflows, and controls your Node.js application needs.
npm install @agentium/coreStart with core. Add the integrations your application needs.
One SDK, connected parts
Start with the capability your product needs. Compose the rest through dedicated APIs, provider adapters, and a shared TypeScript foundation.
Your AI application
6 connected parts
Define the model, instructions, and tools. Add a reusable execution environment with the harness package.
Open guideUse realtime models or compose speech pipelines. Connect carrier adapters for outbound calls.
Open guideGenerate or edit images with OpenAI or Gemini tools, directly or as part of an agent workflow.
Open guideCoordinate specialists, branch on results, and combine agent calls with your application code.
Open guideBring conversation history, saved facts, and retrieved context into the next run.
Open guideTrack provider usage and estimated charges. Set budgets and require approval for selected tools.
Open guideStart small. Add capabilities without changing the foundation.
Start with TypeScript
Choose a model, give it instructions, and run it from TypeScript. Add context and tools as your application grows.
import { Agent, openai } from "@agentium/core";
const productGuide = new Agent({
name: "product-guide",
model: openai("gpt-6-astra"),
instructions: "Explain technical ideas with one concrete example.",
});
const answer = await productGuide.run(
"When should an agent use a tool?",
);
console.log(answer.text);Voice, images & telephony
Speak with users, create images, or manage outbound calls. Choose dedicated adapters for each capability and connect them to your application’s tools and workflows.
Use OpenAI Realtime or Gemini Live, or compose speech recognition, an agent, and speech synthesis with providers such as ElevenLabs and Sarvam. Connect your audio transport separately.
Generate or edit images with OpenAI or Gemini tools. Choose the provider and supported options for your application.
Manage outbound calls through Twilio, Exotel, Telnyx, SignalWire, Vonage, or LiveKit SIP. Track call intents and status; connect voice and audio transport separately.
Build the application
Build on the same foundations whether your product answers questions, creates images, handles calls, or coordinates a team of agents.
How the pieces work together
Context, decisions, tools, and human review belong in the same application flow.
01/ Context
Load the conversation and retrieve the information the agent needs.
Incoming request
“I need help with invoice A104.”
Context loaded
Account history
Session memory
Invoice record
Connected data
Example data. Your storage and retrieval decide what loads.
02/ Routing
Route by the request’s context, using a model or your own application logic. Give each specialist the tools it needs.
Incoming request
“I need help with invoice A104.”
Team routing
Use a model or application logic to choose the next specialist.
03/ Tools
Give the specialist access to the relevant API and prepare the response.
Incoming request
“I need help with invoice A104.”
Specialist at work
Input
id: "A104"
Result
2 invoice items
Draft response
I found invoice A104. The second line item looks like a duplicate of the first. I can issue a credit for it once a teammate confirms.
04/ Approval
Require approval before a selected tool runs, then record what happened.
Incoming request
“I need help with invoice A104.”
Human review
Approval gateThe tool does not run until a reviewer decides. Nothing is called from this page.
Keep control as you grow
Track usage and estimated costs across providers. Add budget checks, tool approvals, tracing, and evaluations as your application grows.
Require a human decision before selected tools execute.
Account for provider usage, estimate charges, and check configured budgets during a run.
Add tracing, metrics, and structured logs through the observability package.
Define test cases and score outputs before you change production behavior.
Inside a run
Subscribe to agent lifecycle and tool events. Connect those signals to your logs, metrics, and traces.
Fits your stack
Choose providers for models, realtime voice, speech, images, and phone calls. Connect your existing services and storage through dedicated adapters and tools.
Add the adapters and credentials you need for your chosen services.
What will you build?
Explore patterns you can adapt to your own product.
Bring account context, ticket routing, and useful tools into the same support flow.
Retrieve source material, split the work, and review the result before it moves on.
Explore voice conversations and browser tasks using Agentium’s dedicated integrations.
Agentium is an open-source TypeScript SDK for building AI applications on Node.js. Core includes agents, tools, memory, teams, workflows, voice adapters, image tools, telephony, and cost accounting. Additional packages provide harnesses, background work, browser automation, observability, and evaluation.
No. Choose from model adapters including OpenAI, Anthropic, Google Gemini, and Ollama, or bring a custom integration. You can select separate providers for text, realtime voice, and speech. Features vary by adapter.
An Agent runs the model and tool-calling loop. The separate @agentium/harness package adds reusable context, skills, tool access, policies, budgets, and sessions around an execution driver. Use a harness when you want to share those controls across agents, teams, or workflows.
Yes, with the relevant memory configuration and storage. Configure persistence for sessions and enable additional memory features as needed. In-memory storage does not survive a process restart.
Yes. Configure approval rules for selected tool calls and connect them to your application’s review flow.
Yes. Use the dedicated voice and telephony APIs or image-generation toolkit for the capabilities your application needs. Voice supports native realtime providers and composed speech pipelines. Carrier adapters handle call control; your application connects the voice runtime and audio transport.
Enable cost accounting to inspect reported usage and estimated charges for each run. Configure budgets to check recorded costs before further requests, and add tracing and metrics through the observability package. Estimates depend on provider usage and available prices; incomplete costs stay visible.
This website describes the SDK and its runtime integrations. You choose the infrastructure on which your application runs. Use the transport and queue guides to connect it to your deployment.
Start with the quickstart, run a small agent, and then add the tools or memory your use case needs. The examples page points to focused recipes.
Run your first agent. Add voice, tools, and workflows as your product takes shape.