OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Tensorlake

Tensorlake is Python-based compute infrastructure for agentic applications, combining a Sandbox API that creates stateful MicroVM execution environments with a serverless function runtime for long-running orchestration and fan-out.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tensorlake — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Tensorlake when an agent application needs isolated code execution or sandbox-backed tools, or when its background work needs serverless orchestration and fan-out.

Who it is for

  • Developers building agents that need isolated environments for tools or LLM-generated code.
  • Teams deploying background agentic applications that require longer-running or fan-out orchestration.
  • Python developers who want SDK or CLI workflows for managing sandboxes.

Documented uses

  • Run an agent or its tools inside a stateful MicroVM sandbox.
  • Execute commands, read and write files, or start processes within a sandbox using the Python SDK.
  • Create and manage sandboxes from the CLI, including command execution and termination.
  • Add long-running orchestration and function fan-out to agent applications.
Before you choose

Requirements & limits

The README directs cloud users to sign up for an account, obtain an API key, and authenticate with the CLI. It documents installation of the Python SDK with pip and distribution of the `tl` CLI as a standalone binary. The repository is public and licensed under Apache-2.0.

  • Tensorlake has distinct sandbox and orchestration roles: MicroVMs handle stateful execution, while the serverless function runtime supports long-running work and fan-out.
  • The README documents Python SDK operations and CLI-based sandbox management.
  • Custom sandbox environments must use a registered Sandbox Image; arbitrary Docker image references are not supported.
  • The repository’s quickstart demonstrates an OpenAI Agents-based city weather tool, but does not establish a general integration guarantee.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Create and run a sandbox with the CLI

Create a Tensorlake sandbox, execute a command inside it, and terminate it.

Before you start

  • Install the standalone tl CLI using the project’s install script.
  • Create a Tensorlake Cloud account, obtain an API key, and authenticate with tl login.

Steps

  1. Run tl sbx create to create a sandbox.

  2. Run tl sbx exec -- sh -lc "printf 'Hello from the sandbox!\n'" to execute a command.

  3. Run tl sbx terminate when finished.

Expected outcome

A sandbox is created, a shell command runs inside it, and the sandbox is terminated.

Guide limitations

  • The documented example uses Tensorlake’s default managed environment; selecting a custom environment requires a registered Sandbox Image.
  • A create-request timeout leaves the sandbox queued and does not cancel it.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
TensorlakeRun an agent or its tools inside a stateful MicroVM sandbox.Cloud, ServerThe README directs cloud users to sign up for an account, obtain an API key, and authenticate with the CLI. It documents installation of the Python SDK with pip and distribution of the `tl` CLI as a standalone binary. The repository is public and licensed under Apache-2.0.
Agentfm CoreRun a containerized agent in a Podman sandbox on a worker machineDesktop, Docker, Self-hostedThe README lists desktop installers for macOS and Linux; it says the Windows app is in progress. Its desktop quick start says the bundled node connects to the public mesh. The README notes that the v1 installers are unsigned and macOS may block the first launch.
PlanoRoute incoming requests to agents based on their declared roles.Self-hosted, ServerPlano is public source code under the Apache-2.0 license. The README describes hosted Plano models free of charge in the US-central region for a first-run developer experience; for production scale it points to running models locally or contacting the project for API keys.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
tensorlakeai/tensorlake · Official homepage title · retained in its source language
How we review sourcesSuggest a correction