Daytona connector for AI agents

Tools your sandbox agent reaches for on Daytona, scoped per user.

CALL ANY TOOL

100 tools for Daytona sandboxes: create, start, stop, fork, and archive sandboxes, run commands and code, read and edit files, run Git operations, and manage snapshots, volumes, registries, and secrets.

daytona_activate_snapshot

Activate snapshot

Activate an inactive Daytona snapshot so it can be used to create sandboxes again. Returns the snapshot object with its updated state. Use daytona_activate_snapshot to restore a snapshot turned off by daytona_deactivate_snapshot.

Parameters

Name

Type

Required

Description

snapshot_id

string

Required

ID of the snapshot, from the `id` field returned by daytona_list_snapshots. Example: 7b1e2d3c-4a5b-6c7d-8e9f-0a1b2c3d4e5f

daytona_archive_sandbox

Archive sandbox

daytona_create_folder

Create folder

daytona_create_sandbox_snapshot

Create sandbox snapshot

daytona_create_snapshot

Create snapshot

daytona_delete_file

Delete file

daytona_delete_session

Delete session

daytona_execute_command

Execute command

daytona_find_in_files

Find in files

daytona_get_current_api_key

Get current api key

daytona_get_port_preview_url

Get port preview url

daytona_get_sandbox_metrics

Get sandbox metrics

daytona_get_session_command

Get session command

daytona_get_toolbox_proxy_url

Get toolbox proxy url

daytona_git_add

Add git

daytona_git_configure_user

Git configure user

daytona_git_list_branches

Git list branches

daytona_git_reset

Reset git

daytona_list_files

List files

daytona_list_registries

List registries

daytona_list_sessions

List sessions

daytona_recover_sandbox

Recover sandbox

daytona_run_code

Run code

daytona_search_files

Search files

daytona_send_session_command_input

Send session command input

daytona_set_file_permissions

Set file permissions

daytona_set_sandbox_autopause_interval

Set sandbox autopause interval

daytona_start_sandbox

Start sandbox

daytona_stop_sandbox

Stop sandbox

daytona_update_registry

Update registry

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Daytona tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["daytona"], toolNames: [
    "daytona_create_sandbox",
    "daytona_execute_command",
    "daytona_git_status"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Run the test suite in the api-dev sandbox and report what failed" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["daytona"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Run the test suite in the api-dev sandbox and report what failed" }],
  tools,
});

// Execute the tool call with the user's vaulted Daytona access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["daytona"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Run the test suite in the api-dev sandbox and report what failed" }],
  tools,
});

// Tool call runs with the user's vaulted Daytona access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["daytona"] }, pageSize: 100,
});

const agent = new Agent({
  name: "sandbox_agent",
  model: "gemini-2.5-pro",
  instruction: "Daytona tools scoped to this user",
  tools,
});

await agent.run("Run the test suite in the api-dev sandbox and report what failed");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Daytona tool. Click to copy, paste into your agent, done.

Sandboxes

Copy the prompt

Copied

Create a sandbox from the python-dev snapshot with 4 CPUs.

Copy the prompt

Copied

List stopped sandboxes labeled project=billing.

Copy the prompt

Copied

Stop the api-dev sandbox, then archive it.

Code and files

Copy the prompt

Copied

Run npm test in the web-dev sandbox.

Copy the prompt

Copied

Search the src folder in the web-dev sandbox for TODO comments.

Copy the prompt

Copied

Get a preview URL for port 3000 in the web-dev sandbox.

Git and snapshots

Copy the prompt

Copied

Show the Git status of the repo in /workspace/app.

Copy the prompt

Copied

Commit the staged changes with the message Fix billing rounding, then push.

Copy the prompt

Copied

Capture the api-dev sandbox as a new snapshot.

SEE HOW AUTH WORKS

Each user connects their own Daytona access token once, and Scalekit sends it with every call. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Daytona

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Daytona

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Daytona

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Daytona

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other developer tools and AI connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Daytona access token looks fine in a demo. In production every sandbox command looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Daytona today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Daytona as the user or through a shared access token?

As the user. Each user connects their own Daytona access token once, and Scalekit sends it with every call. Sandbox, file, and Git changes the agent makes are attributed to that user in your audit trail, not a shared service account.

Where is the Daytona access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Daytona?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example sandbox and file tools without daytona_delete_sandbox, which permanently deletes a sandbox and its filesystem. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Daytona access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent run arbitrary code in a Daytona sandbox?

Only inside a started sandbox, and only if you expose those tools. daytona_execute_command runs a shell command and daytona_run_code runs a Python, JavaScript, or TypeScript snippet. Leave both out of listScopedTools if the agent should only inspect sandboxes, logs, and metrics.