{"id":"tensorlake","name":"Tensorlake","category":"compute","summary":"Run agent code in hosted sandboxes with controlled resources and resumable state.","description":"Tensorlake supplies sandbox and orchestration infrastructure for agents. Its API, Python and TypeScript SDKs, and CLI create execution environments, run commands, move files and manage named sandboxes that can suspend and resume.","url":"https://aiagentstore.ai/services-for-ai-agents/tensorlake","website":"https://www.tensorlake.ai/?utm_source=aiagentstore.ai","docs":"https://docs.tensorlake.ai/sandboxes/quickstart?utm_source=aiagentstore.ai","interfaces":["api","sdk","cli"],"capabilities":["sandbox","code-execution","compute","snapshots"],"humanSetup":"Create an account and select a project and plan. Issue a project API key for SDK use, or authenticate the CLI separately. Set resource limits, timeouts and a budget before scheduling work.","authentication":"SDKs read TENSORLAKE_API_KEY. CLI login authenticates the CLI separately; it does not automatically configure SDK credentials.","billing":"A limited free tier, prepaid credits and paid plans are available. Paid usage meters CPU, memory, disk and snapshot storage. Optional auto-refill can create additional purchases; confirm plan allowances and overages in the account.","firstTask":"Create a short-lived sandbox, run a small command, retrieve its output and files, then explicitly verify that the environment has stopped.","limitations":"Unnamed sandboxes are ephemeral and cannot suspend. Named environments support resume, subject to plan and capacity limits. Suspended state can incur storage charges. CPU and GPU sandboxes use different isolation mechanisms.","readiness":"autonomous-after-setup","paymentMode":"provider-account","agentPayments":"not-verified","verifiedAt":"2026-11-03","verification":"Official documentation reviewed; account onboarding and paid execution not independently tested.","sources":["https://docs.tensorlake.ai/sandboxes/quickstart?utm_source=aiagentstore.ai","https://docs.tensorlake.ai/sandboxes/introduction?utm_source=aiagentstore.ai","https://docs.tensorlake.ai/sandboxes/lifecycle?utm_source=aiagentstore.ai","https://docs.tensorlake.ai/platform/billing?utm_source=aiagentstore.ai","https://www.tensorlake.ai/pricing?utm_source=aiagentstore.ai"],"siteGuide":{"title":"Choose the sandbox lifecycle before starting code","summary":"Provisioned compute, managed isolation and retained execution state require operating infrastructure. An agent can write the workload but cannot provide remote capacity merely by generating code.","url":"https://aiagentstore.ai/services-for-ai-agents/tensorlake#integration-playbook","contentType":"text/html","requiresBrowser":false,"includes":["selection rationale","suggested workflow","acceptance checks","failure recovery","related services"],"basis":"Original AI Agent Store editorial guidance; not an execution benchmark."},"categoryUrl":"https://aiagentstore.ai/services-for-ai-agents/category/compute","tagLinks":[{"id":"api","url":"https://aiagentstore.ai/services-for-ai-agents/tag/api"},{"id":"sdk","url":"https://aiagentstore.ai/services-for-ai-agents/tag/sdk"},{"id":"cli","url":"https://aiagentstore.ai/services-for-ai-agents/tag/cli"},{"id":"sandbox","url":"https://aiagentstore.ai/services-for-ai-agents/tag/sandbox"},{"id":"code-execution","url":"https://aiagentstore.ai/services-for-ai-agents/tag/code-execution"},{"id":"compute","url":"https://aiagentstore.ai/services-for-ai-agents/tag/compute"},{"id":"snapshots","url":"https://aiagentstore.ai/services-for-ai-agents/tag/snapshots"}]}