Daytona

Daytona provides provider-managed remote sandboxes. Use it when you want a remote workspace per task without consuming local compute, especially for SWE-bench and Terminal-Bench smoke tests.

Official Setup Links

Need	Link
Create an account and manage sandboxes	Daytona Dashboard
Create API keys	Daytona API keys page
Getting started docs	Daytona documentation
API key docs	Daytona API keys

First-Time Setup

Create a Daytona account from the official dashboard.
Open the API keys page and create a key with sandbox permissions.
Export the key in the shell that runs AgentCompass.
Run a single task before increasing concurrency.

export DAYTONA_API_KEY="..."
export DAYTONA_API_URL="https://your-daytona-api"  # optional
export DAYTONA_TARGET="your-target"               # optional

DAYTONA_API_KEY is the only value most users need. DAYTONA_API_URL and DAYTONA_TARGET are optional and should be set only when your Daytona workspace requires a non-default API endpoint or target. AgentCompass authentication precedence is:

Source	Use when
`environments.daytona.api_key`	You intentionally keep credentials in a private `--config` file.
`DAYTONA_API_KEY`	Recommended for shell sessions, CI, and shared scripts.
`DAYTONA_API_URL` / `DAYTONA_TARGET`	Optional endpoint and target overrides.

Do not commit Daytona API keys to config/defaults.yaml. Use environment variables or a private config file passed with --config.

Verify Credentials

The most useful verification is an AgentCompass smoke test because it checks credentials, sandbox startup, recipe image selection, file operations, and harness execution together.

Single Terminal-Bench Instance

agentcompass run \
  terminal_bench_2 \
  terminus2 \
  your-model \
  --env daytona \
  --benchmark-params '{"sample_ids":["overfull-hbox"]}' \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY"

This is the recommended provider smoke test because it runs one task and lets the recipe infer the task image.

Provider Params

Common Daytona overrides live under environments.daytona or --env-params:

Field	Use
`api_key`	Private config alternative to `DAYTONA_API_KEY`.
`api_url`	Override the Daytona API endpoint.
`target`	Override the Daytona target.
`image`	Use a Docker image when no recipe should select the image.
`snapshot`	Use a Daytona snapshot for faster or prebuilt startup.
`delete_on_close`	Set `false` while debugging a sandbox.
`sandbox_start_timeout`	Increase when images or snapshots start slowly.
`operation_timeout`	Increase for long file or process operations.
`env_variables`	Inject non-secret environment variables into the sandbox.

SWE-bench Verified

agentcompass run \
  swebench_verified \
  mini_swe_agent \
  your-model \
  --env daytona \
  --benchmark-params '{"sample_ids":["astropy__astropy-12907"]}' \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY"

Recipes set compatible images and workspaces for supported benchmark/provider pairs. Pass --env-params only for deliberate overrides.

Get Started

Key Modules

Environments

Cookbooks

Official Setup Links

First-Time Setup

Verify Credentials

Single Terminal-Bench Instance

Provider Params

SWE-bench Verified

​Official Setup Links

​First-Time Setup

​Verify Credentials

​Single Terminal-Bench Instance

​Provider Params

​SWE-bench Verified

​Related Pages

Official Setup Links

First-Time Setup

Verify Credentials

Single Terminal-Bench Instance

Provider Params

SWE-bench Verified

Related Pages