openkbs

Design, deploy, and manage AI agents and platforms with backend and frontend components.

5|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/open-kbs/openkbs --skill openkbs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openkbs
Source: https://github.com/open-kbs/openkbs/tree/main/templates/.claude/skills/openkbs
Command: npx skills add https://github.com/open-kbs/openkbs --skill openkbs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenKBS provides a complete framework to design, deploy, and manage AI agents and applications, enabling teams to rapidly build capable AI-powered services with scalable deployment.

Core Features & Use Cases

  • Create standalone agents (agent-only mode) or full platforms (platform mode) with backend handlers, frontend components, and elastic services.
  • Manage memory, scheduling, and real-time communication via elastic services (functions, Postgres, Storage, Pulse) for scalable AI apps.
  • Example: Build a multi-agent SaaS platform with centralized orchestration, deploy to cloud, and monitor via dashboards.

Quick Start

Create a new agent with openkbs create my-agent, then push to deploy to the cloud.

Frequently Asked Questions about openkbs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy and orchestrate multi-agent AI platforms?

You can deploy and orchestrate multi-agent AI platforms by defining runtime instructions in Markdown and utilizing elastic services like Postgres, Storage, and Pulse for backend handlers and frontend components.

What is the best way to build a full-stack AI agent application?

Building a full-stack AI agent application is best achieved by combining backend handlers, frontend components, and elastic services to support centralized orchestration and scalable cloud deployment.

Do I need a specific file structure to create a standalone AI agent?

Creating a standalone AI agent requires a SKILL.md file containing frontmatter with a name and description, alongside optional scripts, references, and assets directories for runtime execution.

Can I manage memory and real-time communication for scalable AI apps?

Managing memory and real-time communication for scalable AI apps is supported through integrated elastic services, providing functions, Postgres database connections, Storage, and Pulse scheduling capabilities.

How does the OpenKBS framework handle agent-only mode versus full-stack platforms?

The framework handles agent-only mode by deploying individual agents, while full-stack platforms utilize backend handlers, frontend components, and elastic services for complete multi-agent SaaS applications.

What are the limitations of using Markdown for AI agent runtime instructions?

Markdown limitations for AI agent runtime instructions involve relying strictly on the body content for logic, meaning complex execution requires referencing external scripts and assets rather than native code execution.