Skip to content
Back to search

agents

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/inkeep/agents with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/inkeep/agents'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/inkeep--agents/badge.svg)](/listings/inkeep--agents)

HTML

<a href="/listings/inkeep--agents"><img src="/api/listings/inkeep--agents/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 92 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Inkeep Agents
  2. 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.
  3. Get started with the [docs](https://docs.inkeep.com) or [1-minute quick start](https://docs.inkeep.com/get-started/quick-start).
  4. ## Two ways to build
  5. ### No-Code Visual Builder
  6. A drag-and-drop canvas so any team can create and own the Agents they care about.
  7. <img
  8. src="agents-docs/public/gifs/drag-n-drop.gif"
  9. alt="Visual Builder Demo"
  10. width="100%"
  11. style="border-radius: 10px"
  12. />
  13. ### TypeScript Agents SDK
  14. A code-first framework so engineering teams can build with typesafety, intellisense, CI/CD, and the tools they expect.
  15. ```typescript
  16. import { agent, subAgent } from "@inkeep/agents-sdk";
  17. import { consoleMcp } from "./mcp";
  18. const helloAgent = subAgent({
  19. id: "hello-agent",
  20. name: "Hello Agent",
  21. description: "Says hello",
  22. canUse: () => [consoleMcp],
  23. prompt: `Reply to the user and console log "hello world" with fun variations like h3llo world`,
  24. });
  25. export const basicAgent = agent({
  26. id: "basic-agent",
  27. name: "Basic Agent",
  28. description: "A basic agent",
  29. defaultSubAgent: helloAgent,
  30. subAgents: () => [helloAgent],
  31. });
  32. ```
  33. 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.
  34. ## Use Cases
  35. Inkeep Agents can operate as real-time **AI Chat Assistants**, for example:
  36. - a customer experience agent for help centers, technical docs, or in-app experiences
  37. - an internal copilot to assist your support, sales, marketing, ops, and other teams
  38. Agents can also be used for **AI Workflow Automation** like:
  39. - Creating and updating knowledge bases, documentation, and blogs
  40. - Updating CRMs, triaging helpdesk tickets, and tackling repetitive tasks
  41. ## Platform Overview
  42. **Inkeep Open Source** includes:
  43. - A Visual Builder & TypeScript SDK with 2-way sync
  44. - Multi-agent architecture to support teams of agents
  45. - MCP Tools with credential management
  46. - A UI component library for dynamic chat experiences
  47. - Triggering Agents via MCP, A2A, & Vercel SDK APIs
  48. - Observability via a Traces UI & OpenTelemetry
  49. - Easy deployment using Vercel or Docker
  50. For a full overview, see the [Concepts](https://docs.inkeep.com/concepts) guide.
  51. Interested in a managed platform? Sign up for the [Inkeep Cloud waitlist](https://inkeep.com/cloud-waitlist) or learn about [Inkeep Enterprise](https://inkeep.com/enterprise).
  52. ## Architecture
  53. The Inkeep Agent Platform is composed of several key services and libraries that work together:
  54. - **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.
  55. - **agents-manage-ui**: Visual Builder web interface for creating and managing Agents. Writes to the `agents-api`.
  56. - **agents-sdk**: TypeScript SDK (`@inkeep/agents-sdk`) for declaratively defining Agents and custom tools in code. Writes to `agents-api`.
  57. - **agents-cli**: Includes various handy utilities, including `inkeep push` and `inkeep pull` which sync your TypeScript SDK code with the Visual Builder.
  58. - **agents-ui**: A UI component library of chat interfaces for embedding rich, dynamic conversational AI experiences in web apps.
  59. Under the hood, the framework uses the [Vercel AI SDK](https://ai-sdk.dev/docs/introduction) for interfacing with LLM providers, so it's compatible with Vercel's [`useChat`](https://ai-sdk.dev/docs/ai-sdk-ui) hook and other AI primatives.
  60. ## License and Community
  61. The Inkeep Agent Framework is licensed under the **Elastic License 2.0** ([ELv2](https://www.elastic.co/licensing/elastic-license)) subject to **Inkeep's Supplemental Terms** ([SUPPLEMENTAL_TERMS.md](https://github.com/inkeep/agents/blob/main/SUPPLEMENTAL_TERMS.md)). This is a [fair-code](https://faircode.io/), source-available license that allows broad usage while protecting against certain competitive uses.
  62. 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.
  63. If you'd like to contribute, follow our [contribution guide](https://docs.inkeep.com/community/contributing/overview).
  64. [Join our community](https://docs.inkeep.com/community/inkeep-community) to get support, stay up to date, and share feedback.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.