Overview of the Inkeep Agent Platform

Copy page

With Inkeep, you can create and manage Agents with the No-Code Visual Builder or TypeScript Agents SDK.

Inkeep Agents are often used as:

  • A Customer-facing Agent that you embed as a support assistant in your help center, copilot in your app, or sales chatbot on your marketing site.
  • An Internal Agent accessible from Claude, ChatGPT, Slack, Zendesk, Cursor, and other apps your team uses
  • A Workflow Agent used to automate repetitive tasks at scale, like updating docs, creating blog posts, summarizing sales calls, and more.

Agents are flexible and customizable - they can take on the role you need them to. All powered by the same knowledge of your product and company.

To get started, you can try the open-source edition (this docs site) or to learn about Inkeep Cloud, see here.

Two ways to build your agents

  1. Agent Visual Builder: A no-code interface designed to let both technical and non-technical teams create and manage agents.
Visual Builder Demo

  1. TypeScript Agents SDK: A code-first approach for building and managing agents and multi-agent systems, allowing you to build complex agent systems with the tools your engineering team expects.

    import { agent, agentGraph } from "@inkeep/agents-sdk";

const helloAgent = agent({
  id: "hello-agent",
  name: "Hello Agent",
  description: "A basic agent",
  prompt:
    'You are a basic agent that just says hello. You only reply with the word "hello", but you may do it in different variations like h3110, h3110w0rld, h3110w0rld! etc...',
});

export const graph = agentGraph({
  id: "basic-graph",
  name: "Basic Graph Example",
  description: "A basic graph",
  defaultAgent: helloAgent,
  agents: () => [helloAgent],
});

The Visual Builder and Agents SDK are fully interoperable: your technical and non-technical teams can edit and manage agents in either format and switch or collaborate with others at any time.

Key Concepts

  • Agents: LLM and AI driven decision-making units defined by instructions ('prompts') that can take actions, answer questions, and coordinate with other agents as needed.
  • Graphs: A team of agents that work together to perform complex tasks across your apps and APIs.
  • Tools: The capabilities that agents can invoke. Tools can be your own custom functions or you can leverage our pre-built MCP tools for common integrations.
  • Transfers and Delegations: Relationships between agents. Transfers involve a transfer of control of the chat from one agent to another, and delegation allows an agent to create a sub-task for a different agent.
  • Traces: A log that gives you full visibility into every step of how an agent graph ran. Accessible via UI or OpenTelemetry.

Advanced Features

  • Data Components: Define what agents can output in their messages so they can render rich, interactive UIs (lists, buttons, forms, etc.).
  • Context Fetchers: A way to retrieve and cache data about your user or apps so that an agent has it immediately available in its prompt.
  • Artifacts: A piece of data that can be saved by an agent so it is accessible to other agents or users.
Quick Start