ai-agent

tensorlake

Name: tensorlake
Author: tensorlakeai

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

1,024 stars+1★ this week150 forksPythonUpdated 10/22/2026100% free · open source

What it does

Tensorlake lets you run Python‑based autonomous agents in a fully managed, server‑less sandbox, so you can focus on the agent logic instead of infrastructure.

When to use it

•You need a background worker that continuously polls APIs, processes data, and takes actions without keeping a VM alive.
•Your product requires a secure, isolated execution environment for third‑party AI agents (e.g., custom recommendation or compliance bots).
•You want to prototype an autonomous workflow and then scale it to production with a single deploy command.

Ready-to-paste prompt

tensorlake deploy my_agent --env prod --schedule 'cron(0 */6 * * *)'  # deploys the agent and runs it every 6 hours

Heads up: Tensorlake requires a valid API key for the Tensorlake cloud platform; set it as `TENSORLAKE_API_KEY` in your environment before running any `tensorlake` command, otherwise the CLI will fail with an authentication error.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tensorlake && curl -fsSL https://workflowstacks.com/api/skills/tensorlake/claude-skill -o ~/.claude/skills/tensorlake/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How tensorlake works

Codeflow

Free to inspect

Tensorlake is a very large Rust project (~133k lines across 408 code files, plus 243 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~133k lines · 408 code files · days to read — use, don't read

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Rust · Python

Needs API keys (.env)

Rust 41%Python 39%TypeScript 19%JavaScript 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
Cargo.toml
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide
5
src/tensorlake/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic180 files

docs/Documentation6 files

examples/Examples you can copy3 files

crates/Folder172 files

typescript/Folder154 files

proto/Data models & types3 files

tensorlake.data/Folder2 files

platform/Folder1 files

READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tensorlake && curl -fsSL https://workflowstacks.com/api/skills/tensorlake/claude-skill -o ~/.claude/skills/tensorlake/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

tensorlakeai

Language

Python