HomeBlogPricingCareersDocsGitHubSlack community
Talk to FounderDashboard →
TENSORLAKE·ENGINEERING LOG / VOL. 04·EST. 2024

Engineering log.

Dispatches from the Tensorlake runtime team — how we build the sandbox layer under five million agent workloads, the research that shapes it, and what we shipped this week.

EDITIONQ3 · 2026
POSTS37
AUTHORS16
EngineeringJul 30, 2026·5 min read·◆ FEATURED

Build Your Own CI infrastructure

You get a GitHub runner, and you get a GitHub runner...

DC
David CalaveraSoftware Engineer · Tensorlake
From the community
All community builds →
Community buildsAug 4, 2026

I Forked One AI Agent Into 12 Workers — and Every Clone Woke Up Already Knowing Everything

Chew Loong NianCommunity buildsAug 1, 2026

Getting Started with Tensorlake Sandboxes: Build, Run, and Manage Your First Isolated AI Workload with Python

Raj KumarCommunity buildsJul 30, 2026

Git Without the Clone: Durable, Versioned Workspaces for AI Agents

Rohan Mistry
Sort
Archive —ALL
19 POSTS · UPDATED DAILY
Jul 30, 2026Engineering

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

David CalaveraSoftware Engineer · Tensorlake5 minJul 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 minJul 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 minJul 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 minJul 9, 2026Engineering

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

Diptanu Gon ChoudhuryCEO & Co-founder8 minJun 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 minJun 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 minMay 13, 2026Engineering

Filter and rank: how we schedule sandboxes across every cloudOne primitive — filter, then rank — runs through statefulness, multi-cloud, BYOC, and the data path. A tour of the scheduler behind Tensorlake's sandbox fleet.

Diptanu Gon ChoudhuryCEO & Co-founder14 minMay 1, 2026Engineering

Browser Harness: direct Chrome DevTools Protocol access and a self-healing harness for browser agentsBrowser-use strips their harness to 592 lines and gives the LLM a raw WebSocket to Chrome's DevTools Protocol. When the agent hits a gap, it writes a helper function — and saves it for future runs.

Antonio Jimeno YepesEngineering3 minApr 30, 2026Engineering

How scaffold design affects coding agent benchmark scores: lessons from DroidContextual instruction injection, per-model tool schemas, and planning/execution splits — the harness decisions behind Droid's 77.3% on Terminal-Bench.

Antonio Jimeno YepesEngineering3 min
◆ THE SANDBOX DIGEST

Subscribe for release notes, benchmarks, deep dives.

One dispatch per month from the Tensorlake team — no spam.