Tensorlake — sandbox-native cloud for AI agents

Build agents with sandboxes and serverless orchestration runtime

PyPI Version Python Support License Documentation Slack

Tensorlake is a compute infrastructure platform for building agentic applications with sandboxes.

The Sandbox API creates MicroVM sandboxes which you can use to run agents, or use them as an isolated environment for running tools or LLM generated code.

In addition to stateful VMs, you can also add long running orchestration capabilities to Agents using a serverless function runtime with fan-out capabilities.

Sandboxes

Tensorlake Sandboxes are stateful Firecracker MicroVMs built for instant, stateful execution environments for AI agents — spin up millions of VMs with near-SSD filesystem performance.

Key capabilities

  • Fastest Filesystem I/O — Block-based storage achieving near-SSD speeds inside virtual machines. In SQLite benchmarks (2 vCPUs, 4 GB RAM), Tensorlake completes in 2.45s vs Vercel 3.00s (1.2×), E2B 3.92s (1.6×), Modal 4.66s (1.9×), and Daytona 5.51s (2.2×).
  • Fast startup — Sandboxes created in under a second via Lattice, a dynamic cluster scheduler.
  • Snapshots & cloning — Snapshot at any point to create durable memory and filesystem checkpoints; clone running sandboxes instantaneously across machines.
  • Auto suspend/resume — Sandboxes suspend when idle and resume in under a second without losing any memory or filesystem state.
  • Live migration — Sandboxes automatically move between machines during updates with only a brief pause of a few seconds.
  • Scale — Supports up to 5 million sandboxes in a single project.

Python SDK Installation

pip install tensorlake

CLI Installation

The tl CLI is distributed as a standalone binary, not through PyPI or npm. Install it with the install script:

curl -fsSL https://tensorlake.ai/install | sh

Setup

Sign up at cloud.tensorlake.ai and get your API key.

export TENSORLAKE_API_KEY="your-api-key"
tl login

Create Your First Sandbox (CLI)

Create a sandbox, run a command, and clean up:

# Create a sandbox
tl sbx create --image tensorlake/tensorlake/ubuntu-minimal

# Run a command inside it
tl sbx exec <sandbox-id> -- sh -lc "printf 'Hello from the sandbox!\n'"

# Copy a file into the sandbox
tl sbx cp ./my_script.py <sandbox-id>:/tmp/my_script.py

# Open an interactive terminal
tl sbx ssh <sandbox-id>

# Terminate when done
tl sbx terminate <sandbox-id>

--image expects a sandbox image name such as tensorlake/ubuntu-minimal or a registered Sandbox Image name, not an arbitrary Docker image reference.

Create a Sandbox Programmatically

from tensorlake.sandbox import SandboxClient

client = SandboxClient.for_cloud(api_key="your-api-key")

# Create a sandbox and connect to it
with client.create_and_connect(image="tensorlake/ubuntu-minimal") as sandbox:
    # Run a command
    result = sandbox.run("sh", ["-lc", "printf 'Hello from the sandbox!\\n'"])
    print(result.stdout)  # "Hello from the sandbox!"

    # Write and read files
    sandbox.write_file("/tmp/data.txt", b"some data")
    content = sandbox.read_file("/tmp/data.txt")

    # Start a long-running process
    proc = sandbox.start_process("sleep", ["300"])
    print(proc.pid)

# Sandbox is automatically terminated when the context manager exits

Snapshots

Save the state of a sandbox and restore it later:

# Snapshot a running sandbox
snapshot = client.snapshot_and_wait(sandbox_id)

# Later, create a new sandbox from the snapshot
with client.create_and_connect(snapshot_id=snapshot.snapshot_id) as sandbox:
    # Picks up right where you left off
    result = sandbox.run("ls", ["/tmp"])
    print(result.stdout)

Sandbox Pools

Pre-warm containers for fast startup:

# Create a pool with warm containers
pool = client.create_pool(
    image="tensorlake/ubuntu-minimal",
    warm_containers=3,
)

# Claim a sandbox instantly from the pool
resp = client.claim(pool.pool_id)
sandbox = client.connect(resp.sandbox_id)

# Named sandboxes can be reconnected later by name
named = client.create(image="tensorlake/ubuntu-minimal", name="stable-name")
sandbox = client.connect("stable-name")

Orchestrate

Create orchestration APIs on a distributed runtime with automatic scaling, fan-out capabilities and built-in tracking. The orchestration APIs can be invoked using HTTP requests or using the Python SDK.

Quickstart

Decorate your entrypoint with @application() and functions with @function(). Each function runs in its own isolated sandbox.

Example: City guide using OpenAI Agents with web search and code execution:

from agents import Agent, Runner
from agents.tool import WebSearchTool, function_tool
from tensorlake.applications import application, function, Image

# Define the image with necessary dependencies
FUNCTION_CONTAINER_IMAGE = Image(base_image="python:3.11-slim", name="city_guide_image").run(
    "pip install openai openai-agents"
)

@function_tool
@function(
    description="Gets the weather for a city using an OpenAI Agent with web search",
    secrets=["OPENAI_API_KEY"],
    image=FUNCTION_CONTAINER_IMAGE,
)
def get_weather_tool(city: str) -> str:
    """Uses an OpenAI Agent with WebSearchTool to find current weather."""
    agent = Agent(
        name="Weather Reporter",
        instructions="Use web search to find current weather in Fahrenheit for the city.",
        tools=[WebSearchTool()],  # Agent can search the web
    )
    result = Runner.run_sync(agent, f"City: {city}")
    return result.final_output.strip()

@application(tags={"type": "example", "use_case": "city_guide"})
@function(
    description="Creates a guide with temperature conversion using function_tool",
    secrets=["OPENAI_API_KEY"],
    image=FUNCTION_CONTAINER_IMAGE,
)
def city_guide_app(city: str) -> str:
    """Uses an OpenAI Agent with function_tool to run Python code for conversion."""

    @function_tool
    def convert_to_celsius_tool(python_code: str) -> float:
        """Converts Fahrenheit to Celsius - runs as Python code via Agent."""
        return float(eval(python_code))

    agent = Agent(
        name="Guide Creator",
        instructions="Using the appropriate tools, get the weather for the purposes of the guide. If the city uses Celsius, call convert_to_celsius_tool to convert the temperature, passing in the code needed to convert the temperature to Celsius. Create a friendly guide that references the temperature of the city in Celsius if the city typically uses Celsius, otherwise reference the temperature in Fahrenheit. Only reference Celsius or Fahrenheit, not both.",
        tools=[get_weather_tool, convert_to_celsius_tool],  # Agent can execute this Python function
    )
    result = Runner.run_sync(agent, f"City: {city}")
    return result.final_output.strip()

Deploy to Tensorlake

  1. Set your API keys:
export TENSORLAKE_API_KEY="your-api-key"
tl secrets set OPENAI_API_KEY "your-openai-key"
  1. Deploy:
tl deploy examples/readme_example/city_guide.py

Call via HTTP

# Invoke the application
curl https://api.tensorlake.ai/applications/city_guide_app \
  -H "Authorization: Bearer $TENSORLAKE_API_KEY" \
  --json '"San Francisco"'
# Returns: {"request_id": "beae8736ece31ef9"}

# Get the result
curl https://api.tensorlake.ai/applications/city_guide_app/requests/{request_id}/output \
  -H "Authorization: Bearer $TENSORLAKE_API_KEY"

# Stream results with SSE
curl https://api.tensorlake.ai/applications/city_guide_app \
  -H "Authorization: Bearer $TENSORLAKE_API_KEY" \
  -H "Accept: text/event-stream" \
  --json '"San Francisco"'

FAQ

What is Tensorlake? Tensorlake is the sandbox-native cloud for AI agents — a compute platform for securely running untrusted, LLM-generated code in isolated sandboxes and orchestrating agentic applications at scale.

How do I run untrusted or LLM-generated code safely? Each Tensorlake sandbox is an isolated Firecracker MicroVM, so untrusted or LLM-generated code runs in a hardware-virtualized environment separate from your infrastructure and other sandboxes. Create one with the Python or TypeScript SDK, or the CLI, in a few lines.

How is Tensorlake different from E2B, Modal, or Daytona? Tensorlake is built for heavy filesystem I/O, fast startup, and large-scale fan-out. In SQLite benchmarks (2 vCPUs, 4 GB RAM) it completes in 2.45s versus E2B (3.92s), Modal (4.66s), and Daytona (5.51s), and it supports snapshots, auto suspend/resume, live migration, and up to 5 million sandboxes per project.

Can I checkpoint and resume an AI agent? Yes. Snapshot a running sandbox at any point to capture both memory and filesystem state, then create a new sandbox from that snapshot to pick up exactly where you left off. Sandboxes also auto-suspend when idle and resume in under a second without losing state.

How fast do sandboxes start? Sandboxes are created in under a second via Lattice, a dynamic cluster scheduler. For even faster starts, use sandbox pools to keep warm containers ready to claim instantly.

How do I run code interpreter / tool execution for an LLM agent? Spin up a sandbox as an isolated execution environment for an agent's tools or generated code, run commands or processes inside it, read and write files, and terminate it when done — all from the Python or TypeScript SDK, or the CLI.

What languages and interfaces are supported? Tensorlake provides a Python SDK, a TypeScript SDK, and a standalone CLI (tl), plus an HTTP API for invoking orchestration applications.

How do I get started? Sign up at cloud.tensorlake.ai, run pip install tensorlake for the Python SDK, install the CLI with curl -fsSL https://tensorlake.ai/install | sh, set your TENSORLAKE_API_KEY, and create your first sandbox. See the documentation for full guides.

Learn More

Project links

Data verified by PyPI on Jul 10, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.5.112)

3 maintainers

PyPI data
Data sourced directly from PyPI's database.
Avatar for calavera from gravatar.com calavera Avatar for diptanuc from gravatar.com diptanuc Avatar for eugene_tensorlake from gravatar.com eugene_tensorlake

Credits

Author: Tensorlake Inc.

GitHub Statistics

Data verified by PyPI on Jul 10, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

Requires

Python >=3.10

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tensorlake-0.5.67.tar.gz (2.3 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

tensorlake-0.5.67-cp310-abi3-win_amd64.whl (7.5 MB view details)

Uploaded CPython 3.10+Windows x86-64

tensorlake-0.5.67-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.0 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.17+ x86-64

tensorlake-0.5.67-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (6.8 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.17+ ARM64

tensorlake-0.5.67-cp310-abi3-macosx_11_0_arm64.whl (6.5 MB view details)

Uploaded CPython 3.10+macOS 11.0+ ARM64

File details

Details for the file tensorlake-0.5.67.tar.gz.

File metadata

  • Download URL: tensorlake-0.5.67.tar.gz
  • Upload date:
  • Size: 2.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tensorlake-0.5.67.tar.gz
Algorithm Hash digest
SHA256 5ebf5107d007bdc6db82b509c354fd16fc216a0dae1ef356f6f0f4ce041a0e60
MD5 4412e90f582750d4ea3ad63171d7a9da
BLAKE2b-256 c6022588d8250a9e7805de680690b01800feaf57f599770be0795df332465490

See more details on using hashes here.

Provenance

The following attestation bundles were made for tensorlake-0.5.67.tar.gz:

Publisher: publish_pypi.yaml on tensorlakeai/tensorlake

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tensorlake-0.5.67-cp310-abi3-win_amd64.whl.

File metadata

  • Download URL: tensorlake-0.5.67-cp310-abi3-win_amd64.whl
  • Upload date:
  • Size: 7.5 MB
  • Tags: CPython 3.10+, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tensorlake-0.5.67-cp310-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 6e43a8c86226eea92d1c065bf3fd8d54ed352ef341c55835420304ede46db105
MD5 decf7ef9e6cc982f3abfbed4f4693e6a
BLAKE2b-256 f30f921842b82c4752e6679b24ca5c82bbf8b9cc8ec5e84db3257aacc45aa542

See more details on using hashes here.

Provenance

The following attestation bundles were made for tensorlake-0.5.67-cp310-abi3-win_amd64.whl:

Publisher: publish_pypi.yaml on tensorlakeai/tensorlake

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tensorlake-0.5.67-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for tensorlake-0.5.67-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 f06f0be40e3ccd30528083c9239d0103aca26c0c96cb15d0fedfacd697ff3d21
MD5 5458577ded219e66eaa8b1a3de3085f3
BLAKE2b-256 78f36d5834c8feea7cf2fffffc0cc7b2e568f6c1f5e22ca7d7f088b7592bc5d1

See more details on using hashes here.

Provenance

The following attestation bundles were made for tensorlake-0.5.67-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish_pypi.yaml on tensorlakeai/tensorlake

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tensorlake-0.5.67-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for tensorlake-0.5.67-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 4270f3b2b63305ddf690f1d014298415c197c21605df2ad3b6223f21effd58ba
MD5 2dddc715c5245c85cd3a3d425935c37a
BLAKE2b-256 f53d947baf98e72b5b4047b301c817a101a9de0acd4c52c3fbec7743ad75a746

See more details on using hashes here.

Provenance

The following attestation bundles were made for tensorlake-0.5.67-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: publish_pypi.yaml on tensorlakeai/tensorlake

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tensorlake-0.5.67-cp310-abi3-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for tensorlake-0.5.67-cp310-abi3-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 04a6b5b24d551c9e1d13ade19d128b2d83fef26ccb8d1a19e991266cc742d387
MD5 43c702d3b9ab739ac36880db5f39d1ca
BLAKE2b-256 2e84a27ecb179ce541fc3c6dd3a9abcf2956c79b834bbe85385958b08be0d829

See more details on using hashes here.

Provenance

The following attestation bundles were made for tensorlake-0.5.67-cp310-abi3-macosx_11_0_arm64.whl:

Publisher: publish_pypi.yaml on tensorlakeai/tensorlake

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.5.112

4 files

0.5.111

4 files

0.5.110

4 files

0.5.109

4 files

0.5.108

4 files

0.5.107

4 files

0.5.103

5 files

0.5.97

5 files

0.5.95

5 files

0.5.94

5 files

0.5.92

5 files

0.5.91

5 files

0.5.89

5 files

0.5.88

5 files

0.5.85

5 files

0.5.77

5 files

0.5.76

5 files

0.5.75

5 files

0.5.70

5 files

This release

0.5.67 This release

5 files

0.5.66

5 files

0.5.63

5 files

0.5.59

5 files

0.5.58

5 files

0.5.57

5 files

0.5.55

5 files

0.5.54

5 files

0.5.53

5 files

0.5.52

5 files

0.5.51

5 files

0.5.50

5 files

0.5.47

5 files

0.5.46

5 files

0.5.44

5 files

0.5.43

5 files

0.5.41

5 files

0.5.40

5 files

0.5.38

5 files

0.5.37

5 files

0.5.36

5 files

0.5.35

5 files

0.5.34

5 files

0.5.33

5 files

0.5.32

5 files

0.5.31

5 files

0.5.30

5 files

0.5.29

5 files

0.5.28

5 files

0.5.27

5 files

0.5.26

5 files

0.5.25

5 files

0.5.24

5 files

0.5.23

5 files

0.5.22

5 files

0.5.21

5 files

0.5.20

5 files

0.5.19

5 files

0.5.18

5 files

0.5.17

5 files

0.5.16

5 files

0.5.15

5 files

0.5.14

5 files

0.5.13

5 files

0.5.12

5 files

0.5.11

5 files

0.5.10

5 files

0.5.9

5 files

0.5.8

5 files

0.5.7

5 files

0.5.6

5 files

0.5.5

5 files

0.5.4

5 files

0.5.3

5 files

0.5.2

5 files

0.5.1

5 files

0.5.0

5 files

0.4.50

5 files

0.4.49

5 files

0.4.48

5 files

0.4.45

5 files

0.4.44

5 files

0.4.43

5 files

0.4.42

5 files

0.4.41

5 files

0.4.40

5 files

0.4.39

5 files

0.4.38

5 files

0.4.37

5 files

0.4.35

5 files

0.4.34

5 files

0.4.33

5 files

0.4.32

5 files

0.4.31

5 files

0.4.30

4 files

0.4.29

4 files

0.4.27

4 files

0.4.26

4 files

0.4.25

4 files

0.4.23

5 files

0.4.22

5 files

0.4.21

5 files

0.4.20

5 files

0.4.19

5 files

0.4.18

5 files

0.4.17

5 files

0.4.16

5 files

0.4.14

5 files

0.4.11

5 files

0.4.9

5 files

0.4.4

2 files

0.4.3

2 files

0.4.2

2 files

0.4.1

2 files

0.4.0

2 files

0.3.13

2 files

0.3.12

2 files

0.3.11

2 files

0.3.10

2 files

0.3.9

2 files

0.3.8

2 files

0.3.7

2 files

0.3.6

2 files

0.3.5

2 files

0.3.4

2 files

0.3.3

2 files

0.3.2

2 files

0.3.1

2 files

0.2.101

2 files

0.2.100

2 files

0.2.99

2 files

0.2.98

2 files

0.2.97

2 files

0.2.96

2 files

0.2.95

2 files

0.2.94

2 files

0.2.93

2 files

0.2.92

2 files

0.2.91

2 files

0.2.90

2 files

0.2.88

2 files

0.2.87

2 files

0.2.86

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page