Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. Tensorlake
Developer Tools
Tensorlake icon

Tensorlake

by Tensorlake

Tensorlake provides isolated microVM sandboxes where AI agents can run untrusted, LLM-generated code. It also offers hosted Git and a versioned filesystem for agent harnesses, evals and CI.

API·Contact for pricing

Visit tensorlake.ai(opens in a new tab)

About Tensorlake

Key features of Tensorlake

  • Firecracker microVM sandboxes
  • Persistent or ephemeral sandboxes
  • Sleep on inactivity and instant wake
  • Snapshot, suspend and resume
  • Versioned POSIX filesystem
  • Hosted Git
  • Python and TypeScript SDKs and a CLI
  • Scales from one to thousands

Who Tensorlake is for

  • Developers building agent harnesses
  • Teams running RL rollouts and evals
  • Teams building scalable CI

How to use Tensorlake

  1. 1

    Step 1: Get an API key from the dashboard.

  2. 2

    Step 2: Install the SDK with npm i @tensorlakeai/tensorlake or the Python package.

  3. 3

    Step 3: Create a sandbox and run a command in it.

  4. 4

    Step 4: Mount a versioned filesystem if the agent needs durable storage.

  5. 5

    Step 5: Snapshot, suspend or scale the sandboxes as needed.

Tensorlake FAQ

What isolation do sandboxes use?

Firecracker microVMs, isolated from the harness.

Do sandboxes keep state?

Yes. They sleep on inactivity and wake instantly, and sessions can run for hours or days.

Which languages can I use?

The SDK examples are Python and TypeScript, plus a CLI.

How is storage handled?

A versioned filesystem mounts as an ordinary POSIX directory with autosave and snapshots.

Details

Pricing
Contact for pricingThe site has a pricing page and a demo option.
Type
API
Platforms
  • API
  • CLI
Categories
Developer ToolsData
Added
Sep 16, 2026
Tensorlake iconPublisherTensorlake

Built from public sources

We put this page together from Tensorlake’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Tensorlake.

Work at Tensorlake? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
Chainbase AI iconChainbase AIChainbase · Contact for pricingChainbase AI is a set of tools that gives AI agents access to onchain data from 90+ blockchains. It includes agent skills, a command-line tool and an MCP server.Developer Tools · Contact for pricingMem0 iconMem0Mem0 · FreemiumMem0 is an AI-focused api for developer tools workflows, giving users practical model-powered capabilities through a dedicated product or developer interface.Developer Tools · FreemiumDocling iconDoclingIBM · FreeDocling is an AI-native product for document conversion toolkit that extracts structured content from PDFs and other formats for AI and RAG pipelines.Developer Tools · Free