Engineering Log — The Tensorlake Blog

EngineeringSep 16, 2026·7 min read·◆ FEATURED

Run multi-container agent evals on Tensorlake with Harbor

Harbor 0.23.0 can run Docker Compose tasks on Tensorlake. Each task boots as one MicroVM with a Docker daemon inside, so an agent’s MCP server, database, browser, or game server runs next to it as its own container.

Shanshan WangApplied AI · Tensorlake

From the community

All community builds →

Community buildsSep 13, 2026

Sort

Archive —ALL

22 POSTS · UPDATED DAILY

Sep 16, 2026Engineering

Run multi-container agent evals on Tensorlake with HarborHarbor 0.23.0 can run Docker Compose tasks on Tensorlake. Each task boots as one MicroVM with a Docker daemon inside, so an agent’s MCP server, database, browser, or game server runs next to it as its own container.

Shanshan WangApplied AI · Tensorlake7 min Aug 29, 2026Engineering

Dynamic Firewall Policies for Sandboxes.Every Tensorlake sandbox that carries a network policy sits behind an egress firewall on the host. A walk through the enforcement path, plus two recent improvements: live policy updates and per-connection hostname checks.

Salvador GironèsSoftware Engineer · Tensorlake12 min Aug 26, 2026Engineering

Strengthening agent evaluation environments.Tensorlake Sandboxes now support dynamic network policies in Harbor: public, allowlist, or no-network per trial phase, switched on a running sandbox without a restart.

Shanshan WangApplied AI · Tensorlake4 min Jul 30, 2026Engineering

Build Your Own CI infrastructureYou get a GitHub runner, and you get a GitHub runner...

David CalaveraSoftware Engineer · Tensorlake5 min Jul 28, 2026Product

Introducing Tensorlake BYOC: Serverless Sandboxes in Your Private CloudRun Tensorlake Sandboxes on compute you own across AWS, GCP, Azure, CoreWeave, Nebius, and bare metal. Same APIs, images, and SDKs as Tensorlake Cloud, with compute, storage, and workload traffic inside your own network.

Diptanu Gon ChoudhuryCEO / Co-founder5 min Jul 22, 2026Engineering

Run Devin Outposts on Tensorlake Sandboxes.Cognition keeps the agent loop; execution runs inside a Tensorlake sandbox you control. We built the integration, and you can clone and run it today.

Shanshan WangApplied AI · Tensorlake7 min Jul 13, 2026Engineering

Firecracker disk snapshots in O(changed bytes), not O(disk size)We added copy-on-write image layering inside Firecracker's block device, and the disk got faster, not slower. Snapshots pause the VM for tens of milliseconds and cost only what changed, so a running Postgres barely notices them, at any disk size.

Diptanu Gon ChoudhuryCEO / Co-founder10 min Jul 9, 2026Engineering

Zero-copy TLS ingress with kTLS and splice(2) for sandboxes

Diptanu Gon ChoudhuryCEO & Co-founder8 min Jun 24, 2026Engineering

Accelerating Harbor with Tensorlake.Tensorlake runs the real task Docker images for Harbor on microVM sandboxes. On Terminal-Bench 2.1 the oracle passes all 89 tasks in 36m 44s — every image published, cold starts in seconds.

Shanshan WangApplied AI · Tensorlake6 min Jun 5, 2026Engineering

Tensorlake Sandboxes as the runtime for Claude Managed Agents.Run Claude Managed Agents on Tensorlake Sandboxes: you keep the control of self-hosting, and drop the always-on box. The short version — the server goes away.

Shanshan WangApplied AI · Tensorlake7 min

Engineering log.