
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.
APIContact for pricing
Step 1: Get an API key from the dashboard.
Step 2: Install the SDK with npm i @tensorlakeai/tensorlake or the Python package.
Step 3: Create a sandbox and run a command in it.
Step 4: Mount a versioned filesystem if the agent needs durable storage.
Step 5: Snapshot, suspend or scale the sandboxes as needed.
Firecracker microVMs, isolated from the harness.
Yes. They sleep on inactivity and wake instantly, and sessions can run for hours or days.
The SDK examples are Python and TypeScript, plus a CLI.
A versioned filesystem mounts as an ordinary POSIX directory with autosave and snapshots.
Chainbase AIChainbase 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.