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

# Flint AI

> Discover, prove, and protect your AI agents

# Make AI earn it

Ship AI agents with confidence.

<Card title="Flint AI on GitHub" icon="github" href="https://github.com/sandbox-quantum/flintai-cli">
  Source code, example agents, and issue tracking
</Card>

Trust in AI agents should be earned, not assumed. Flint AI helps you verify agent reliability before production.

## Flint AI family

|                 | **Platform**                                                        | **CLI**                                                |
| --------------- | ------------------------------------------------------------------- | ------------------------------------------------------ |
| **What**        | Full stack AgentOps platform                                        | Command-line scanner and evaluator                     |
| **Where**       | Cloud-based (GitHub integration + SDK)                              | Local, on your machine                                 |
| **Best for**    | Teams managing agents in production                                 | Developers testing agents locally                      |
| **Setup**       | GitHub Action + SDK wrapper                                         | `npm install -g flintai`                               |
| **Get started** | [Discover quickstart →](/flintai/platform/getting-started/discover) | [Scan quickstart →](/flintai/cli/scan/getting-started) |

### Works with all major frameworks

<div style={{display: 'flex', flexWrap: 'wrap', gap: '40px', alignItems: 'center', marginTop: '16px'}}>
  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/claude.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=d085c41df40fafb2ea377efe3bbc8ea0" alt="Claude Agents SDK" title="Claude Agents SDK" height="56" noZoom data-path="images/frameworks/claude.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/langchain.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=463e80393b48bd882996cf2e54c6ae61" alt="LangChain" title="LangChain" height="56" noZoom data-path="images/frameworks/langchain.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/crewai.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=9c80843734146b9fe7ff1eac214c5ea8" alt="CrewAI" title="CrewAI" height="56" noZoom data-path="images/frameworks/crewai.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/anthropic.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=bfe34183e179050fbfc771fabf6dd8db" alt="Anthropic SDK" title="Anthropic SDK" height="56" noZoom data-path="images/frameworks/anthropic.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/openai.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=8f7719f2c3e264dc126057a5b416d300" alt="OpenAI SDK" title="OpenAI SDK" height="56" noZoom data-path="images/frameworks/openai.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/mcp.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=36a60f666ff683f9cc5ca0524a981294" alt="MCP servers" title="MCP servers" height="56" noZoom data-path="images/frameworks/mcp.svg" />

  <img src="https://mintcdn.com/sandboxaq/2_u5qeh8JPl_KDDW/images/frameworks/autogen.svg?fit=max&auto=format&n=2_u5qeh8JPl_KDDW&q=85&s=37f5754191f37a904ac87b870acb4a97" alt="Microsoft AutoGen" title="Microsoft AutoGen" height="56" noZoom data-path="images/frameworks/autogen.svg" />
</div>

## Why Flint AI?

Developers are shipping agents faster than they can test them. Agents ignore instructions, call the wrong tools, or fabricate answers. You need confidence before production.

* **Scan code** for security risks and misconfigurations
* **Run adversarial evaluations** to test behavior under attack
* **Monitor runtime sessions** to see what agents actually do
* **Enforce guardrails** to prevent issues before they ship

## Get started

<CardGroup cols={2}>
  <Card title="Flint AI Platform" icon="shield-check" href="/flintai/platform">
    Discover AI agents in your code, monitor runtime sessions, and enforce guardrails. Full stack AgentOps.
  </Card>

  <Card title="Flint AI CLI" icon="terminal" href="/flintai/cli">
    Static code analysis and runtime evaluation for AI agents. Fast local scanning and testing.
  </Card>
</CardGroup>