> ## Documentation Index
> Fetch the complete documentation index at: https://splinter.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Control and coordination infrastructure for multi-agent AI systems

# What is Splinter?

Splinter is **control and coordination infrastructure** for multi-agent AI systems. It sits between your agents and LLM providers, ensuring your agents don't go rogue.

<CardGroup cols={2}>
  <Card title="Control Layer" icon="sliders" href="/control/overview">
    Runtime controls. Budget limits, rate limiting, circuit breakers, decision locks.
  </Card>

  <Card title="Coordination Layer" icon="arrows-split-up-and-left" href="/coordination/overview">
    Multi-agent collaboration. Shared state, checkpointing, handoffs, goal tracking.
  </Card>
</CardGroup>

## The Problem

Without proper controls, AI agents will:

* **Spend unlimited money** — A single agent can rack up thousands in API costs
* **Loop forever** — Agents get stuck repeating the same actions
* **Overwrite each other** — Multiple agents writing to the same state = chaos
* **Crash with no recovery** — Hours of work lost when something fails

## The Solution

```python theme={null}
from splinter import Splinter

s = Splinter(
    openai_key="sk-...",
    max_budget=5.0,   # Stop at $5
    max_steps=50,     # Stop after 50 calls
)

result = await s.run("researcher", "Research AI trends")
print(f"Cost: ${s.cost:.4f}")  # Always know what you spent
```

Splinter prevents all of these problems with a simple, pluggable architecture.

## Architecture

```mermaid theme={null}
flowchart TB
    Agents["<b>YOUR AGENTS</b><br/>Agent 1 | Agent 2 | Agent 3 | ..."]
    
    Splinter["<b>SPLINTER</b> (Local - Free)<br/><br/>🛡️ <b>CONTROL</b> | 🤝 <b>COORDINATION</b><br/>─────────────────────────<br/>Budget limits | Shared state<br/>Rate limiting | Checkpointing<br/>Circuit breakers | Schema validation<br/>Decision locks | Goal tracking<br/>Loop detection | Action eligibility"]
    
    LLM[OpenAI / Claude<br/>Gemini / Grok]
    Cloud[☁️ Splinter Cloud<br/>(Paid API Key)]
    
    Agents --> Splinter
    Splinter --> LLM
    Splinter --> Cloud
    
    style Agents fill:#DBEAFE,stroke:#3B82F6,stroke-width:2px,color:#000
    style Splinter fill:#8B0000,stroke:#6c0404,stroke-width:3px,color:#fff
    style LLM fill:#D1FAE5,stroke:#10B981,stroke-width:2px,color:#000
    style Cloud fill:#E0E7FF,stroke:#6366F1,stroke-width:2px,color:#000
```

## Local vs Cloud

<CardGroup cols={2}>
  <Card title="Local (Free)" icon="laptop">
    All Control and Coordination features run entirely on your machine. No external dependencies.
  </Card>

  <Card title="Cloud (Paid)" icon="cloud" href="/cloud/overview">
    Add an API key for live dashboard, remote control, deadlock detection, and more.
  </Card>
</CardGroup>

## Quick Links

<CardGroup cols={3}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get up and running in 5 minutes
  </Card>

  <Card title="Concepts" icon="lightbulb" href="/concepts">
    Understand the core ideas
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Full API documentation
  </Card>
</CardGroup>
