> ## Documentation Index
> Fetch the complete documentation index at: https://vvennela-ftl-18-95.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to FTL

> Zero-trust control plane for AI coding agents

## What is FTL?

FTL is a **zero-trust control plane for AI coding agents**. Run Claude Code, Codex, Aider, or Kiro inside an isolated Docker sandbox with shadow credentials, parallel adversarial testing, and human-in-the-loop approval — without ever giving the agent access to your real secrets or filesystem.

> [card] [Quickstart](https://vvennela-ftl-18-95.mintlify.site/quickstart.md)
>
> Get up and running with FTL in under 5 minutes

> [card] [Installation](https://vvennela-ftl-18-95.mintlify.site/installation.md)
>
> Detailed installation and setup instructions

> [card] [How it works](https://vvennela-ftl-18-95.mintlify.site/concepts/how-it-works.md)
>
> Learn about FTL's architecture and security model

> [card] [CLI reference](https://vvennela-ftl-18-95.mintlify.site/cli/setup.md)
>
> Complete command-line interface documentation

## Why FTL?

AI coding agents are powerful but untrustworthy by construction. FTL provides the safety layer that makes them practical:

> [card] Isolated execution
>
> Agents run in Docker containers with no access to your host filesystem or real credentials

> [card] Shadow credentials
>
> Your real API keys never enter the sandbox — agents work with safe placeholder values

> [card] Human approval
>
> Every change requires explicit review before touching your project

> [card] Adversarial testing
>
> Tests generate in parallel while the agent codes, catching issues immediately

> [card] Credential linting
>
> Automatic scanning for leaked secrets and dangerous operations

> [card] Multi-agent support
>
> Works with Claude Code, Codex, Aider, and Kiro

## How it works

When you run a task, FTL executes an 8-stage pipeline:

```bash theme={null}
ftl code "build login component with Supabase auth"
```

**1. Snapshot**

Rsync your project state to `~/.ftl/snapshots/<id>`

**2. Boot**

Reuse a persistent container or start fresh (per project)

**3. Inject**

Shadow credentials replace real keys inside the sandbox

**4. Agent ∥ Tests**

The coding agent runs while adversarial tests generate in parallel

**5. Run tests**

Pre-generated tests execute the moment the agent finishes

**6. Lint**

Diff scanned for credentials and dangerous operations

**7. Diff**

Computed on demand; file-level review of all changes

**8. Approve**

You review, ask questions, and merge or reject

> [!NOTE]
>
> The agent runs entirely inside Docker. It never sees your real API keys or your host filesystem. Nothing touches your project without explicit approval.

## Key features

> [accordion] Zero-trust security model
>
> FTL operates on the principle that agents are untrustworthy by construction. Every layer is designed to prevent credential leaks and unauthorized filesystem access:
>
> * Shadow credentials generated for each session
> * Optional network proxy that swaps shadow values for real ones at the HTTP layer
> * Bedrock Guardrails integration for hard-blocking merges with detected secrets

> [accordion] Parallel test generation
>
> While your agent writes code, FTL simultaneously generates adversarial tests using your chosen LLM model:
>
> * No wall-clock time added — tests run immediately when the agent finishes
> * Supports Anthropic, AWS Bedrock, and OpenAI via LiteLLM
> * Manual test re-runs available in interactive mode

> [accordion] Persistent containers
>
> FTL maintains one container per project path to eliminate cold-start overhead:
>
> * Workspace wiped and restored from snapshot on each task
> * Installed packages persist in `/home/ftl/.local/`
> * Agent conversation history preserved across tasks
> * Node.js pre-warmed in background during boot

> [accordion] AWS integration
>
> Optional AWS-backed capabilities for production use:
>
> * S3 snapshot storage
> * CloudWatch session tracing
> * Secrets Manager for credential management
> * Bedrock Guardrails for diff safety

## Supported agents

FTL works with four popular AI coding agents:

| Agent | Key | Requires |
| - | - | - |
| Claude Code | `claude-code` | `ANTHROPIC_API_KEY` |
| Codex | `codex` | `OPENAI_API_KEY` |
| Aider | `aider` | `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` |
| Kiro | `kiro` | AWS credentials + browser login |

> [card] [Learn more about agents](https://vvennela-ftl-18-95.mintlify.site/guides/agents.md)
>
> See detailed configuration and authentication for each agent

## Philosophy

> Agents are untrustworthy by construction. FTL is the layer that makes them safe to use anyway.

The agent cannot have skin in the game. The human must. Every change requires explicit approval before it touches the real filesystem.

## Next steps

> [card] [Run your first task](https://vvennela-ftl-18-95.mintlify.site/quickstart.md)
>
> Complete the 5-minute quickstart guide

> [card] [Configure for production](https://vvennela-ftl-18-95.mintlify.site/guides/aws-setup.md)
>
> Set up AWS integration for S3, CloudWatch, and Guardrails

> [card] [Interactive shell](https://vvennela-ftl-18-95.mintlify.site/guides/interactive-shell.md)
>
> Learn about follow-up instructions and session management

> [card] [Shadow credentials](https://vvennela-ftl-18-95.mintlify.site/concepts/shadow-credentials.md)
>
> Deep dive into credential security


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.