tensorlake

What it is and what it does

Tensorlake is a compute platform for building AI agents with isolated execution environments. It provides two main capabilities: Sandbox API for creating stateful Firecracker MicroVMs that run agents or isolated tools, and an orchestration runtime for serverless functions with fan-out scaling. Sandboxes support snapshots, cloning, auto-suspend/resume, and live migration between machines. The platform also includes a FilesystemClient for managing durable, versioned file trees without mounting them.

The SDK depends on httpx, websocket-client, websockets, pydantic, grpcio, and protobuf for communication and serialization. It targets developers building agentic systems that need strong isolation, fast startup, and stateful execution. Setup requires an API key and Python 3.10 or later. The package is actively maintained and has no known vulnerabilities.

Use it for:

• Run untrusted or user-generated code in isolated sandboxes for AI agents without risking the host system.
• Pre-warm sandbox pools for fast agent startup and claim them on demand for near-instant execution.
• Snapshot sandbox state at checkpoints and restore later to resume agent work without re-initialization.
• Build multi-step orchestration workflows where each function runs in its own isolated sandbox with automatic scaling.
• Store and version large model weights and agent artifacts using the FilesystemClient with direct object-store streaming.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Tensorlake provides a Python SDK for building agentic applications using isolated Firecracker MicroVM sandboxes and a serverless orchestration runtime with automatic scaling.

Yes, if you are building agentic applications that require isolated execution environments and serverless orchestration. The active maintenance, recent releases, and lack of known vulnerabilities are positive signals. However, verify the unclear license status before production use, and confirm pricing and scaling limits align with your workload. Medium install friction is manageable for most teams.

Install

tensorlake on PyPI

pip install tensorlake

uv add tensorlake

poetry add tensorlake

Installing tensorlake

Before you install

Medium install friction due to compiled wheels across multiple platforms (arm64, x86_64, Windows). Active maintenance with a release 5 days ago and 987 repository stars suggests ongoing development. Requires Python 3.10 or later.

License in practice

License status is unclear—no SPDX identifier or raw license text is available. Verify the license terms before adopting in production or commercial contexts.

Quickstart

pip install tensorlake

from tensorlake.sandbox import SandboxClient

client = SandboxClient.for_cloud(api_key="your-api-key")
with client.create_and_connect(image="tensorlake/ubuntu-minimal") as sandbox:
    result = sandbox.run("sh", ["-lc", "echo hello"])
    print(result.stdout)

Requires a Tensorlake API key from cloud.tensorlake.ai and Python 3.10+.

Verify before relying

• Exact performance benchmarks (2.45s SQLite claim) and whether they apply to typical workloads.
• Pricing model and cost implications for scaling to millions of sandboxes.
• Whether the 5 million sandbox limit per project is a hard constraint or a service tier.
• Specific Python versions beyond 3.10 that are actively tested and supported.

Package facts

Evidence: tensorlake-0.5.103-cp310-abi3-macosx_11_0_arm64.whl; tensorlake-0.5.103-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; tensorlake-0.5.103-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; tensorlake-0.5.103-cp310-abi3-win_amd64.whl

Tags

More Distributed Computing packages