tensorlake
Tensorlake SDK for agent sandboxes and sandbox-native orchestration
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Tensorlake API key from cloud.tensorlake.ai and Python 3.10+.
- 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.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text is available. Verify the license terms before adopting in production or commercial contexts.
last release 2026-08-09 (5 days) · last repo commit 2026-08-14 · 987 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 134,274 downloads/mo, #11,481 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on it.
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
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.
Requires a Tensorlake API key from cloud.tensorlake.ai and Python 3.10+.
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)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
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 6 packageshttpxwebsocket-clientwebsocketspydanticgrpcioprotobuf |
| Maintenance | Actively maintained 5 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 134,274 / month, #11,481 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
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
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “microvm orchestration”
- tensorlakeTensorlake provides a Python SDK for building agentic applications…
- dagster-cloudDagster Cloud is a managed orchestration platform that deploys and…
- kailash-enterpriseA Rust-compiled workflow orchestration engine that executes the same…
Give your agent the search over MCP, or paste the wish link into any chat.
More Distributed Computing packages
gRPC Python is an HTTP/2-based RPC framework that enables you to define and call remote procedures across network boundaries using protocol buffers for serialization.
Install it if you need RPC communication in a distributed system or are integrating with existing gRPC services.
execnet lets you spawn and communicate with Python interpreters across local processes, remote hosts, and different platforms, using a simple API for task distribution and inter-process messaging.
However, the aging maintenance status (275 days since last release) means you should verify it meets your concurrency and performance needs before committing to a…
Cloudpickle extends Python's standard pickle module to serialize lambda functions, interactively-defined functions and classes, and other constructs that the default pickle cannot handle, making it suitable for cluster computing and remote code execution.
Install it if you need to serialize lambda functions, interactively-defined code, or non-standard Python constructs for cluster computing or distributed execution.
Provides a unified, open()-compatible Python API for streaming large files from remote storage (S3, GCS, Azure, HDFS, SFTP, HTTP) and local filesystems, with transparent compression support.
Install it if you work with large files on cloud storage or remote systems and want to avoid writing boilerplate around multiple SDKs.
Portalocker provides cross-platform file locking with support for exclusive and shared locks, plus Redis-based distributed locks and process-aware PID file locking.
Install it if you need file or process coordination; the optional extras (pywin32, redis) are only required for specific lock types.
Ray is a distributed computing framework that scales Python applications from a single machine to multi-node clusters, providing abstractions for parallel tasks, stateful actors, and shared objects.
See also blaxel · k8s-agent-sandbox · agent-framework-core · daytona · e2b · openai-agents · agent-framework · prime-sandboxes · apache-flink-libraries · agent-framework-foundry-local