SandBaseSandBase
Start building

Agent-native delivery platform for builders and FDEs

Connect your Agent
to the real world.

Find capabilities. Build workflows. Deliver real work.

Browse the StoreStart with Setup
From capabilities to agent deliveryModels, APIs, and Skills flow into an Agent workflow, which can be delivered to an application, an AI tool, or a schedule.CAPABILITIESModels · APIs · SkillsAGENT WORKFLOWDefine the workBuildTestDeliverDELIVERYAI tool · API · Schedule
Choose the capabilities an Agent needs, define the workflow, then deliver it where the work happens.

Three ways to use SandBase

Use it in your local AI tools, call it from your app, or build a reusable Agent.

01→

Use in your local AI tools

Pick useful capabilities from SandBase, run setup once, and use them in Codex, Claude, Cursor, or Kiro.

02→

Call an API

Copy a working request for a Model, search, scraping, data, or SaaS API.

03→

Build an Agent

Define the job, give it tools, test it, then publish or schedule it.

A deliverable workflow

Turn a question into work you can hand over.

Research, enrich, and deliver a source-backed brief from one reusable workflow.

Research workflow from question to customer briefA customer research question is processed by a workflow that searches sources, enriches company data, and returns a customer brief.BUSINESS QUESTIONResearch a companyRESEARCH AGENTSearch live sourcesAdd company dataBuild the briefDELIVERABLECustomer briefResearch workflow from question to customer briefA customer research question is processed by a workflow that searches sources, enriches company data, and returns a customer brief.BUSINESS QUESTIONResearch a companyRESEARCH AGENTSearch live sourcesAdd company dataBuild the briefDELIVERABLECustomer brief
A reusable research Agent turns a customer question into a source-backed brief.

Setup

Use SandBase inside your AI tool.

Choose the Models, APIs, and Agents you need. Setup makes them available in the local AI tools you already use.

Works with the tools you already use
Codex
Claude Code
Cursor
Kiro
Windsurf
OpenCode
Gemini CLI
Qwen Code
Warp
ChatGPT
Claude Desktop
Kimi CLI
Connect SandBase Setup to an AI toolA connection passes through SandBase Setup and makes selected capabilities available in an AI tool.YOUR AI TOOLCodex · ClaudeCONNECT ONCESandBase SetupAVAILABLE TOOLSModels · APIsConnect SandBase Setup to an AI toolA connection passes through SandBase Setup and makes selected capabilities available in an AI tool.YOUR AI TOOLSCodex · Claude · CursorCONNECT ONCESandBase SetupAVAILABLE TOOLSModels · APIs · Agents
Connect one AI tool, choose what it can use in SandBase Setup, and make those capabilities available.
QUICK STARTbash
$ curl -fsSL https://sandbase.ai/install.sh | sh -s -- --client codex
Guided authorization · no keys in your shell history

APIs

Call one capability from your product.

Use a capability directly. Reuse it inside an Agent when the work grows.

Call a capability with an APIA request travels from an app to a SandBase capability, then a structured response returns to the app.YOUR PRODUCTOne requestCAPABILITYSearch APIRESPONSEStructured data
Call one capability from an application and receive a structured response.
ModelsAdd reasoning, vision, audio, image, and embedding models.Search APIsLet your Agent search the live web and return sources.Data extractionTurn webpages and files into clean data your Agent can use.SaaS APIsConnect to business systems, social data, and workflow tools.Agent templatesStart from working examples and adapt them to your use case.SkillsReuse packaged instructions and code inside Agent workflows.
Browse APIs →Browse Agents →Browse Skills →

Build Agent

Build your Agent before you connect it.

Define the job, give it the right capabilities, and see the result before delivery.

Build an Agent
Build, test, and deliver an Agent workflowAn Agent workflow moves from a defined job to a test run and then to a delivered result.01Define02Test a run03Deliver
Define an Agent, test a run, then deliver it to an AI tool, API, or schedule.

Why SandBase

From a business need to a delivered Agent.

Find capabilities, build an Agent, deliver the work, and see every run in one place.

Find the capability the work needs.

Browse Models, APIs, Skills, and ready-made Agents that already do useful work.

Find
Test
Reuse

FAQ

Choose the right way to use SandBase.

Setup puts tools inside your AI app. APIs let your product call one tool directly. Build Agent is for reusable, multi-step work.

Who is SandBase for?+

SandBase is for builders who need working AI capabilities quickly, and FDEs who need to turn customer requirements into reusable Agent workflows.

Should I start with Setup, APIs, or Build Agent?+

Use Setup when you want tools inside Codex, Claude, Cursor, or Kiro. Use APIs when your product needs one tool, like search or image generation. Use Build Agent when the job has multiple steps and should be reused.

What is in the Store?+

The Store is where you find reusable Agent capabilities: Models, APIs, ready-made Agents, and Skills. You can test them, copy them, install them into Setup, or clone them into Build Agent.

What is an Agent workflow?+

An Agent workflow is a reusable job with instructions and tools. It can research a customer, enrich leads, monitor competitors, triage GitHub issues, or run another repeatable process.

What happens after I build an Agent?+

You can test it, publish it so apps and AI tools can call it, or schedule it to run automatically. Every execution becomes a Run with input, output, trace, and status.

What are Webhooks for?+

Webhooks notify your system when async model, API, or Agent work finishes or fails. They are delivery notifications, not tools inside the Agent.

Start with something real

Start simple. Deliver more when you need it.

Install tools into your AI app, call one API, or build an Agent workflow for repeatable delivery.

Explore the StoreCreate a workspace