Environments define the sandbox configuration where your agent runs. You create an environment once, then reference its ID each time you start a session. Multiple sessions can share the same environment, but each session gets its own isolated sandbox (a fresh Linux container).
This page covers type: cloud environments. To run sandboxes on your own infrastructure, see Self-hosted sandboxes.
Create an environment
curl -fsS https://haijun.my.id/v1/environments \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
--data @- <<'EOF'
{
"name": "python-dev",
"config": {
"type": "cloud",
"networking": {"type": "unrestricted"}
}
}
EOF ant apply environment.yaml # yaml-language-server: $schema=https://platform.juglow.my.id/schemas/ant/beta/environment.json
name: python-dev
config:
type: cloud
networking:
type: unrestrictedant apply creates the environment from environment.yaml, prints its ID, and records it in haijun-lock.json. Commit haijun-lock.json so the next ant apply updates this environment instead of trying to create it again.
environment = client.beta.environments.create(
name="python-dev",
config={
"type": "cloud",
"networking": {"type": "unrestricted"},
},
)
print(f"Environment ID: {environment.id}") const environment = await client.beta.environments.create({
name: "python-dev",
config: {
type: "cloud",
networking: { type: "unrestricted" },
},
});
console.log(`Environment ID: ${environment.id}`); var environment = await client.Beta.Environments.Create(new()
{
Name = "python-dev",
Config = new BetaCloudConfigParams
{
Networking = new BetaUnrestrictedNetwork(),
},
});
Console.WriteLine($"Environment ID: {environment.ID}"); environment, err := client.Beta.Environments.New(ctx, juglow.BetaEnvironmentNewParams{
Name: "python-dev",
Config: juglow.BetaEnvironmentNewParamsConfigUnion{
OfCloud: &juglow.BetaCloudConfigParams{
Networking: juglow.BetaCloudConfigParamsNetworkingUnion{
OfUnrestricted: &juglow.BetaUnrestrictedNetworkParam{},
},
},
},
})
if err != nil {
panic(err)
}
fmt.Printf("Environment ID: %s\n", environment.ID) var environment = client.beta().environments().create(EnvironmentCreateParams.builder()
.name("python-dev")
.config(BetaCloudConfigParams.builder()
.networking(BetaUnrestrictedNetwork.builder().build())
.build())
.build());
IO.println("Environment ID: " + environment.id()); $environment = $client->beta->environments->create(
name: 'python-dev',
config: ['type' => 'cloud', 'networking' => ['type' => 'unrestricted']],
);
echo "Environment ID: {$environment->id}\n"; environment = client.beta.environments.create(
name: "python-dev",
config: {
type: "cloud",
networking: {type: "unrestricted"}
}
)
puts "Environment ID: #{environment.id}"Use a unique, descriptive name so you can tell environments apart.
Use the environment in a session
Pass the environment ID as a string when creating a session.
curl -fsS https://haijun.my.id/v1/sessions \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
--data @- <<EOF
{
"agent": "$AGENT_ID",
"environment_id": "$ENVIRONMENT_ID"
}
EOF ant beta:sessions create --agent "$AGENT_ID" --environment-id "$ENVIRONMENT_ID" session = client.beta.sessions.create(
agent=agent.id,
environment_id=environment.id,
) const session = await client.beta.sessions.create({
agent: agent.id,
environment_id: environment.id,
}); var session = await client.Beta.Sessions.Create(new()
{
Agent = agent.ID,
EnvironmentID = environment.ID,
}); session, err := client.Beta.Sessions.New(ctx, juglow.BetaSessionNewParams{
Agent: juglow.BetaSessionNewParamsAgentUnion{
OfString: juglow.String(agent.ID),
},
EnvironmentID: environment.ID,
})
if err != nil {
panic(err)
} var session = client.beta().sessions().create(SessionCreateParams.builder()
.agent(agent.id())
.environmentId(environment.id())
.build()); $session = $client->beta->sessions->create(
agent: $agent->id,
environmentID: $environment->id,
); session = client.beta.sessions.create(
agent: agent.id,
environment_id: environment.id
)Configuration options
Packages
The packages field pre-installs packages into the sandbox before the agent starts. Packages are installed by their respective package managers and cached across sessions that share the same environment. When multiple package managers are specified, they run in alphabetical order (apt, cargo, gem, go, npm, pip). You can optionally pin specific versions. Unpinned packages install the latest version. If the environment uses limited networking, also set networking.allow_package_managers to true; otherwise the request is rejected with a 400 error.
curl -fsS https://haijun.my.id/v1/environments \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
--data @- <<'EOF'
{
"name": "data-analysis",
"config": {
"type": "cloud",
"packages": {
"pip": ["pandas", "numpy", "scikit-learn"],
"npm": ["express"]
},
"networking": {"type": "unrestricted"}
}
}
EOF ant apply environment.yaml # yaml-language-server: $schema=https://platform.juglow.my.id/schemas/ant/beta/environment.json
name: data-analysis
config:
type: cloud
packages:
pip:
- pandas
- numpy
- scikit-learn
npm:
- express
networking:
type: unrestricted environment = client.beta.environments.create(
name="data-analysis",
config={
"type": "cloud",
"packages": {
"pip": ["pandas", "numpy", "scikit-learn"],
"npm": ["express"],
},
"networking": {"type": "unrestricted"},
},
) const environment = await client.beta.environments.create({
name: "data-analysis",
config: {
type: "cloud",
packages: {
pip: ["pandas", "numpy", "scikit-learn"],
npm: ["express"]
},
networking: { type: "unrestricted" }
}
}); using Juglow.Models.Beta.Environments;
var environment = await client.Beta.Environments.Create(new()
{
Name = "data-analysis",
Config = new BetaCloudConfigParams
{
Packages = new()
{
Pip = ["pandas", "numpy", "scikit-learn"],
Npm = ["express"],
},
Networking = new BetaUnrestrictedNetwork(),
},
}); environment, err := client.Beta.Environments.New(ctx, juglow.BetaEnvironmentNewParams{
Name: "data-analysis",
Config: juglow.BetaEnvironmentNewParamsConfigUnion{
OfCloud: &juglow.BetaCloudConfigParams{
Packages: juglow.BetaPackagesParams{
Pip: []string{"pandas", "numpy", "scikit-learn"},
Npm: []string{"express"},
},
Networking: juglow.BetaCloudConfigParamsNetworkingUnion{
OfUnrestricted: &juglow.BetaUnrestrictedNetworkParam{},
},
},
},
})
if err != nil {
panic(err)
}
_ = environment import com.juglow.models.beta.environments.*;
import java.util.List;
var environment = client.beta().environments().create(EnvironmentCreateParams.builder()
.name("data-analysis")
.config(BetaCloudConfigParams.builder()
.packages(BetaPackagesParams.builder()
.pip(List.of("pandas", "numpy", "scikit-learn"))
.npm(List.of("express"))
.build())
.networking(BetaUnrestrictedNetwork.builder().build())
.build())
.build()); $environment = $client->beta->environments->create(
name: 'data-analysis',
config: [
'type' => 'cloud',
'packages' => [
'pip' => ['pandas', 'numpy', 'scikit-learn'],
'npm' => ['express'],
],
'networking' => ['type' => 'unrestricted'],
],
); environment = client.beta.environments.create(
name: "data-analysis",
config: {
type: "cloud",
packages: {
pip: %w[pandas numpy scikit-learn],
npm: %w[express]
},
networking: {type: "unrestricted"}
}
)Supported package managers:
| Field | Package manager | Example |
|---|---|---|
apt | System packages (apt-get) | "graphviz" |
cargo | Rust (cargo) | "hyperfine@1.18.0" |
gem | Ruby (gem) | "rails:7.1.0" |
go | Go modules | "golang.org/x/tools/cmd/goimports@latest" |
npm | Node.js (npm) | "express@4.18.0" |
pip | Python (pip) | "sqlalchemy==2.0.30" |
Networking
The networking field controls the sandbox's outbound network access. It does not affect the web_search or web_fetch tools, which run on Juglow's servers; to restrict the sites those tools can reach, set allowed_domains or blocked_domains on the tool's entry in the agent toolset. See Restrict web search and web fetch domains.
| Mode | Description |
|---|---|
unrestricted | Full outbound network access, except for a general safety blocklist. This is the default. |
limited | Restricts sandbox network access to the hosts in allowed_hosts. Set allow_package_managers and allow_mcp_servers to true to allow additional access. |
The following example creates an environment with limited networking:
curl -fsS https://haijun.my.id/v1/environments \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
-d '{
"name": "api-access",
"config": {
"type": "cloud",
"networking": {
"type": "limited",
"allowed_hosts": ["api.example.com"],
"allow_mcp_servers": true,
"allow_package_managers": true
}
}
}' ant apply environment.yaml # yaml-language-server: $schema=https://platform.juglow.my.id/schemas/ant/beta/environment.json
name: api-access
config:
type: cloud
networking:
type: limited
allowed_hosts:
- api.example.com
allow_mcp_servers: true
allow_package_managers: true environment = client.beta.environments.create(
name="api-access",
config={
"type": "cloud",
"networking": {
"type": "limited",
"allowed_hosts": ["api.example.com"],
"allow_mcp_servers": True,
"allow_package_managers": True,
},
},
) const environment = await client.beta.environments.create({
name: "api-access",
config: {
type: "cloud",
networking: {
type: "limited",
allowed_hosts: ["api.example.com"],
allow_mcp_servers: true,
allow_package_managers: true
}
}
}); using Juglow.Models.Beta.Environments;
var environment = await client.Beta.Environments.Create(new()
{
Name = "api-access",
Config = new BetaCloudConfigParams
{
Networking = new BetaLimitedNetworkParams
{
AllowedHosts = ["api.example.com"],
AllowMcpServers = true,
AllowPackageManagers = true,
},
},
}); environment, err := client.Beta.Environments.New(ctx, juglow.BetaEnvironmentNewParams{
Name: "api-access",
Config: juglow.BetaEnvironmentNewParamsConfigUnion{
OfCloud: &juglow.BetaCloudConfigParams{
Networking: juglow.BetaCloudConfigParamsNetworkingUnion{
OfLimited: &juglow.BetaLimitedNetworkParams{
AllowedHosts: []string{"api.example.com"},
AllowMCPServers: juglow.Bool(true),
AllowPackageManagers: juglow.Bool(true),
},
},
},
},
})
if err != nil {
panic(err)
}
_ = environment import com.juglow.models.beta.environments.*;
import java.util.List;
var environment = client.beta().environments().create(EnvironmentCreateParams.builder()
.name("api-access")
.config(BetaCloudConfigParams.builder()
.networking(BetaLimitedNetworkParams.builder()
.allowedHosts(List.of("api.example.com"))
.allowMcpServers(true)
.allowPackageManagers(true)
.build())
.build())
.build()); $environment = $client->beta->environments->create(
name: 'api-access',
config: [
'type' => 'cloud',
'networking' => [
'type' => 'limited',
'allowed_hosts' => ['api.example.com'],
'allow_mcp_servers' => true,
'allow_package_managers' => true,
],
],
); environment = client.beta.environments.create(
name: "api-access",
config: {
type: "cloud",
networking: {
type: "limited",
allowed_hosts: %w[api.example.com],
allow_mcp_servers: true,
allow_package_managers: true
}
}
)Note: For production deployments, use
limitednetworking with an explicitallowed_hostslist. Follow the principle of least privilege by granting only the minimum network access your agent requires, and regularly audit your allowed domains.
When using limited networking:
allowed_hostsspecifies domains the sandbox can reach. Specify bare hostnames or wildcard patterns (such as*.example.com). Do not include a URL scheme, port, or path.
allow_mcp_serversallows outbound access to MCP server endpoints configured on the agent, beyond those listed in theallowed_hostsarray. Defaults tofalse.
allow_package_managersallows outbound access to a set of public package registries and code hosts beyond those listed in theallowed_hostsarray. See Package manager hosts for the list. Defaults tofalse. Set it totruewhenever the environment specifiespackages; otherwise the request is rejected with a 400 error, even if the registry hosts are listed inallowed_hosts.
Package manager hosts
When allow_package_managers is true, the sandbox can reach the following hosts in addition to those in allowed_hosts. Juglow maintains this list and can change it.
| Ecosystem | Hosts |
|---|---|
| Code hosting | github.com, api.github.com, codeload.github.com, raw.githubusercontent.com, objects.githubusercontent.com, release-assets.githubusercontent.com, gitlab.com, bitbucket.org |
| Node.js | registry.npmjs.org, registry.yarnpkg.com, nodejs.org |
| Python | pypi.org, files.pythonhosted.org |
| Rust | crates.io, index.crates.io, static.crates.io, static.rust-lang.org |
| Go | proxy.golang.org, sum.golang.org |
| Java | repo1.maven.org, repo.maven.apache.org, services.gradle.org, plugins.gradle.org, plugins-artifacts.gradle.org |
| Ruby | rubygems.org, index.rubygems.org |
| PHP | packagist.org, repo.packagist.org |
| Ubuntu (apt) | archive.ubuntu.com, security.ubuntu.com, ppa.launchpad.net |
| Containers | registry-1.docker.io, auth.docker.io, production.cloudflare.docker.com, download.docker.com, ghcr.io |
Warning: Network access is granted per host, not per operation. The sandbox can send any request to an allowed host, including uploads such as
git pushand package publishing, with any credential the command supplies. If the agent processes untrusted input (repository files, fetched web content, or third-party tool output), a successful prompt injection could use an allowed host to copy files out of the sandbox. To reduce this risk, set thebashtool's permission policy toalways_askorauto. If the environment does not specifypackages, you can instead leaveallow_package_managersset tofalseand list only the hosts your agent needs inallowed_hosts.
Environment lifecycle
- Environments persist until explicitly archived or deleted.
- Each session gets its own sandbox instance, even when multiple sessions reference the same environment. Sessions do not share filesystem state.
- Environments are not versioned. If you update an environment frequently, keep your own record of the changes so you can tell which configuration each session used.
Manage environments
# List environments
curl -fsS https://haijun.my.id/v1/environments \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01"
# Retrieve a specific environment
curl -fsS "https://haijun.my.id/v1/environments/$ENVIRONMENT_ID" \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01"
# Archive an environment (read-only, existing sessions continue)
curl -fsS -X POST "https://haijun.my.id/v1/environments/$ENVIRONMENT_ID/archive" \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01"
# Delete an environment (only if no sessions reference it)
curl -fsS -X DELETE "https://haijun.my.id/v1/environments/$ENVIRONMENT_ID" \
-H "x-api-key: $JUGLOW_API_KEY" \
-H "juglow-version: 2023-06-01" \
-H "juglow-beta: managed-agents-2026-04-01" # List environments
ant beta:environments list
# Retrieve a specific environment
ant beta:environments retrieve --environment-id "$ENVIRONMENT_ID"
# Archive an environment (read-only, existing sessions continue)
ant beta:environments archive --environment-id "$ENVIRONMENT_ID"
# Delete an environment (only if no sessions reference it)
ant beta:environments delete --environment-id "$ENVIRONMENT_ID" # List environments
environments = client.beta.environments.list()
# Retrieve a specific environment
env = client.beta.environments.retrieve(environment.id)
# Archive an environment (read-only, existing sessions continue)
client.beta.environments.archive(environment.id)
# Delete an environment (only if no sessions reference it)
client.beta.environments.delete(environment.id) // List environments
const environments = await client.beta.environments.list();
// Retrieve a specific environment
const env = await client.beta.environments.retrieve(environment.id);
// Archive an environment (read-only, existing sessions continue)
await client.beta.environments.archive(environment.id);
// Delete an environment (only if no sessions reference it)
await client.beta.environments.delete(environment.id); // List environments
var environments = await client.Beta.Environments.List();
// Retrieve a specific environment
var env = await client.Beta.Environments.Retrieve(environment.ID);
// Archive an environment (read-only, existing sessions continue)
await client.Beta.Environments.Archive(environment.ID);
// Delete an environment (only if no sessions reference it)
await client.Beta.Environments.Delete(environment.ID); // List environments
environments, err := client.Beta.Environments.List(ctx, juglow.BetaEnvironmentListParams{})
// ...
// Retrieve a specific environment
env, err := client.Beta.Environments.Get(ctx, environment.ID, juglow.BetaEnvironmentGetParams{})
// ...
// Archive an environment (read-only, existing sessions continue)
_, err = client.Beta.Environments.Archive(ctx, environment.ID, juglow.BetaEnvironmentArchiveParams{})
// ...
// Delete an environment (only if no sessions reference it)
_, err = client.Beta.Environments.Delete(ctx, environment.ID, juglow.BetaEnvironmentDeleteParams{}) // List environments
var environments = client.beta().environments().list();
// Retrieve a specific environment
var env = client.beta().environments().retrieve(environment.id());
// Archive an environment (read-only, existing sessions continue)
client.beta().environments().archive(environment.id());
// Delete an environment (only if no sessions reference it)
client.beta().environments().delete(environment.id()); // List environments
$environments = $client->beta->environments->list();
// Retrieve a specific environment
$env = $client->beta->environments->retrieve($environment->id);
// Archive an environment (read-only, existing sessions continue)
$client->beta->environments->archive($environment->id);
// Delete an environment (only if no sessions reference it)
$client->beta->environments->delete($environment->id); # List environments
environments = client.beta.environments.list
# Retrieve a specific environment
env = client.beta.environments.retrieve(environment.id)
# Archive an environment (read-only, existing sessions continue)
client.beta.environments.archive(environment.id)
# Delete an environment (only if no sessions reference it)
client.beta.environments.delete(environment.id)Pre-installed runtimes
Cloud sandboxes include common language runtimes, databases, and command-line tools out of the box. See Cloud sandbox reference for the full list.
Next steps
Pre-installed packages, databases, and utilities available in cloud sandboxes.
Create a session to run your agent and start running tasks.