Datalayer Runtimes

Overview

Datalayer sells Jupyter-based compute for AI agents. A "Runtime" is a remote kernel you create on demand from the datalayer_core Python SDK (client.create_runtime(environment=..., timeout=...)), the TypeScript client or the CLI, then call execute() on; variables persist between calls within the session, which makes it closer to a code interpreter than to an online judge. Environments are preset: a Python CPU environment and a GPU "AI Environment", each with its own CPU, memory and GPU limits and an hourly burning rate. Secrets are injected as environment variables. Datalayer also hosts the open-source Jupyter MCP Server (BSD-3-Clause, about 1.3k stars) at mcp.datalayer.run so MCP clients such as Claude Code, Codex and Cursor can drive notebooks and sandboxes, and ships the BSD-3-Clause agent-runtimes server for hosting agents on Datalayer runtimes or locally.

Runtimes are time-boxed (timeout in minutes; default not stated on the SDK page) and the environments are described as stateless, so persistent work goes into named snapshots that capture installed packages, files and in-memory variables and can be restored into a new runtime. The isolation mechanism is not documented and no pricing, free tier, regions or compliance details are published outside the JavaScript-rendered marketing site; the SDKs (BSD-3-Clause) were still being pushed in November 2026. Treat it as a young but actively developed kernel-as-a-service rather than a hardened sandbox platform.

Notable

• datalayer_core SDK 1.2.28 on PyPI (BSD-3-Clause); core and agent-runtimes repos pushed on 9 November 2026
• Hosted Jupyter MCP Server at mcp.datalayer.run with OAuth 2.1 sign-in and a Claude Code plugin
• Snapshots capture packages, files and variables but not active network connections

Datalayer Runtimes specifications

Facts from Datalayer Runtimes’s public documentation, verified November 9, 2026. Performance numbers are vendor claims.

Strengths and trade-offs

Strengths

• You want a stateful Jupyter kernel an agent can call repeatedly, with GPU environments
• You need to snapshot an environment (packages, files, variables) and restore it later
• You are driving notebooks from an MCP client and want a hosted MCP server

Trade-offs

• Isolation technology, pricing, free tier, regions and compliance are not documented on fetchable pages
• Runtimes are time-boxed in minutes and environments are stateless without snapshots
• Small community footprint (core repo about 17 stars) and a fast-moving SDK
• No self-hosting of the runtime service

Good fit for: Agents that need a stateful, snapshot-able Jupyter kernel (CPU or GPU) rather than a one-shot run.

Use cases Datalayer Runtimes fits

• Code interpreters: Stateful, snapshot-able Jupyter kernels (CPU or GPU) as a service, for agents that need a kernel rather than a one-shot run.
• GPU workloads: GPU-backed Jupyter kernels as a service for agents that need a stateful kernel with accelerators.

How Datalayer Runtimes compares

See all Datalayer Runtimes alternatives →

Frequently asked questions

Sources

1. datalayer.ai
2. core.datalayer.tech/python/
3. core.datalayer.tech/python/Runtimes
4. core.datalayer.tech/python/Environments
5. github.com/datalayer/core
6. github.com/datalayer/agent-runtimes
7. github.com/datalayer/jupyter-mcp-server
8. pypi.org/pypi/datalayer_core/json