StackOne Agent Tools provide a powerful way to build AI agents that can interact with various business systems through our unified APIs. The Python SDK offers rich integrations with popular AI frameworks like LangChain, CrewAI, and LangGraph.

​
Why StackOne for AI Agents?

StackOne simplifies building B2B SaaS agents by providing:
  1. Unified API Access - Standardized interfaces across different SaaS providers
  2. AI-First Design - Tools designed specifically for AI agent development
  3. Multi-Tenant Support - Built-in handling of customer accounts and permissions
  4. Standardized Data Models - Consistent data structures across providers

​
Architecture Overview

The StackOne Agent Tools consist of three main components:
  1. Unified API - Our standardized API layer that normalizes data across different providers
  2. Toolsets - Language-specific SDKs that wrap the unified API into AI-friendly tools
  3. Dashboard & Accounts - Central management of your integrations and API keys

​
Key Concepts

  • Initialize a ToolSet: Create a StackOneToolSet instance to access unified business APIs
  • Filter Tools: Use glob patterns like "hris_*" to get specific tool categories
  • Execute Tools: Call business system APIs using tool.call() or tool.execute()
  • Multi-Tenant: Each tool execution requires an account_id for customer isolation

​
Python Framework Integrations

LangChain

Build sophisticated agents with LangChain

CrewAI

Multi-agent workflows and collaboration

LangGraph

Complex stateful agent workflows

OpenAI

Direct OpenAI function calling

​
Core Guides

Getting Started

Universal guide covering both SDKs

Tool Filtering

Advanced patterns for tool selection

Meta Tools

Dynamic tool discovery (Beta)

OpenAPI Tools

Use any OpenAPI spec as tools

​
Next Steps

  1. Set up your first agent
  2. Learn about tool filtering
  3. Explore Meta Tools

​
Resources