内容摘录
Inkeep Agents
Build AI Agents with a **No-Code Visual Builder** or **TypeScript SDK**. Agents can be edited in either with **full 2-way sync**, so technical and non-technical teams can create and manage Agents in one platform.
Get started with the docs or 1-minute quick start.
Two ways to build
No-Code Visual Builder
A drag-and-drop canvas so any team can create and own the Agents they care about.
<img
src="agents-docs/public/gifs/drag-n-drop.gif"
alt="Visual Builder Demo"
width="100%"
style="border-radius: 10px"
/>
TypeScript Agents SDK
A code-first framework so engineering teams can build with typesafety, intellisense, CI/CD, and the tools they expect.
The **Visual Builder and TypeScript SDK are fully interoperable**: technical and non-technical teams can edit and manage Agents in either format and collaborate with others at any time.
Use Cases
Inkeep Agents can operate as real-time **AI Chat Assistants**, for example:
a customer experience agent for help centers, technical docs, or in-app experiences
an internal copilot to assist your support, sales, marketing, ops, and other teams
Agents can also be used for **AI Workflow Automation** like:
Creating and updating knowledge bases, documentation, and blogs
Updating CRMs, triaging helpdesk tickets, and tackling repetitive tasks
Platform Overview
**Inkeep Open Source** includes:
A Visual Builder & TypeScript SDK with 2-way sync
Multi-agent architecture to support teams of agents
MCP Tools with credential management
A UI component library for dynamic chat experiences
Triggering Agents via MCP, A2A, & Vercel SDK APIs
Observability via a Traces UI & OpenTelemetry
Easy deployment using Vercel or Docker
For a full overview, see the Concepts guide.
Interested in a managed platform? Sign up for the Inkeep Cloud waitlist or learn about Inkeep Enterprise.
Architecture
The Inkeep Agent Platform is composed of several key services and libraries that work together:
**agents-api**: An API that handles configuration of Agents, Sub Agents, MCP Servers, Credentials, and Projects with a REST API. Additionally, it exposes Agent execution and evaluation. The API tracks conversation state and emits OTEL traces.
**agents-manage-ui**: Visual Builder web interface for creating and managing Agents. Writes to the agents-api.
**agents-sdk**: TypeScript SDK (@inkeep/agents-sdk) for declaratively defining Agents and custom tools in code. Writes to agents-api.
**agents-cli**: Includes various handy utilities, including inkeep push and inkeep pull which sync your TypeScript SDK code with the Visual Builder.
**agents-ui**: A UI component library of chat interfaces for embedding rich, dynamic conversational AI experiences in web apps.
Under the hood, the framework uses the Vercel AI SDK for interfacing with LLM providers, so it's compatible with Vercel's useChat hook and other AI primatives.
License and Community
The Inkeep Agent Framework is licensed under the **Elastic License 2.0** (ELv2) subject to **Inkeep's Supplemental Terms** (SUPPLEMENTAL_TERMS.md). This is a fair-code, source-available license that allows broad usage while protecting against certain competitive uses.
Inkeep is designed to be extensible and open: use the LLM provider of your choice, use Agents via standard protocols, and easily deploy and self-host Agents in your own infra.
If you'd like to contribute, follow our contribution guide.
Join our community to get support, stay up to date, and share feedback.