Quickstart

Get up and running with Firecase in under 5 minutes.

1. Create an Account

2. Get Your API Key

Navigate to Settings → API Keys and create a new API key. Keep this safe — you'll need it to authenticate.

Bash

export FIRECASE_API_KEY="fc_live_..."

3. Create Your First Instance

An instance is a persistent sandbox environment. Create one with a simple API call:

Bash

curl -X POST https://api.firecase.ai/instances \
  -H "Authorization: Bearer $FIRECASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-first-sandbox"
  }'

4. Start the VM

Start the VM to boot your sandbox. This takes about 150ms:

Bash

curl -X POST https://api.firecase.ai/instances/{instance_id}/vm \
  -H "Authorization: Bearer $FIRECASE_API_KEY"

5. Execute Code

Run commands in your sandbox using the exec endpoint:

Bash

curl -X POST https://api.firecase.ai/instances/{instance_id}/exec \
  -H "Authorization: Bearer $FIRECASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "command": ["python3", "-c", "print(\"Hello from Firecase!\")"]
  }'

The response includes the command output:

JSON

{
  "exit_code": 0,
  "stdout": "Hello from Firecase!\n",
  "stderr": ""
}

6. Read and Write Files

Write a file to the sandbox:

Bash

curl -X POST https://api.firecase.ai/instances/{instance_id}/files \
  -H "Authorization: Bearer $FIRECASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "path": "/home/user/hello.py",
    "content": "print(\"Hello from a file!\")"
  }'

Then execute it:

Bash

curl -X POST https://api.firecase.ai/instances/{instance_id}/exec \
  -H "Authorization: Bearer $FIRECASE_API_KEY" \
  -d '{"command": ["python3", "/home/user/hello.py"]}'

7. Create a Checkpoint

Snapshot the current state of your sandbox. You can restore to this point later:

Bash

curl -X POST https://api.firecase.ai/instances/{instance_id}/checkpoints \
  -H "Authorization: Bearer $FIRECASE_API_KEY" \
  -d '{"label": "after-setup"}'

Next Steps

Read about Instances and VMs to understand the core model
Explore the full API Reference for all available endpoints
Follow the AI Code Execution guide for agent integration patterns

Introduction

Installation