Tensorlake

@tensorlake

Scalable Sandbox and Orchestration Infrastructure for Agents at tensorlake.ai

San Francisco, CA

tensorlake.ai

Replies Reposts Media Articles

Tensorlake
@tensorlake
Sep 3
We added one SDK operation for this: Python: Sandbox.get_or_create() TypeScript: Sandbox.getOrCreate() Pass it a stable name, such as an agent session ID. It returns a running sandbox by connecting to the existing one, resuming it when suspended, or creating it when it does not
Shanshan Wang
@cooltxeel
Aug 31
One thing I noticed after building several sandbox integrations: The harness/application still ends up managing parts of the sandbox lifecycle and the session-to-sandbox binding: reconnecting, resuming, handling restarts, and tracking which sandbox belongs to which session. For
1
Tensorlake
@tensorlake
Sep 2
Tensorlake's dynamic network policies let you change the network boundary on a running sandbox, which is especially useful for practical agent workflows. - Coding agents need network access to clone repos and install dependencies. - They probably shouldn’t keep unrestricted
Sebastian Buzdugan
@sebuzdugan
Sep 1
Article
Your Coding Agent Has Your AWS Keys and an Open Internet Connection
The agent needs the network to install its dependencies. Then it runs code a model wrote, in the same box, with the same unrestricted egress, next to your credentials file. Both of those things cannot...
1
Tensorlake
@tensorlake
Sep 1
This is what powers the dynamic network policy support we added to @harborframework , allowing agents to switch network policies without restarting the running environment.
Diptanu Choudhury
@diptanu
Aug 31
We shipped a comprehensive update to Tensorlake's egress traffic and firewall infrastructure for sandboxes. Users can now update almost all aspects of traffic control while a sandbox is running. This lets a sandbox start up, download or configure tools, and then lock down before
00:00
Tensorlake
@tensorlake
Sep 1
This newsletter introduced how @tensorlake Git Repositories and Cloud Volumes give agents durable, versioned workspaces. Here’s a hands-on example of the Git side in action. Instead of cloning a repo into every sandbox, an agent can mount it as a workspace, keep changes durable
Tensorlake
@tensorlake
Aug 31
If you haven’t checked out the new filesystem and Git features in @tensorlake sandboxes yet, this is a good one to take a quick look at. tensorlake.beehiiv.com/p/agent-state-…
1
Tensorlake
@tensorlake
Aug 31
Sharing a practical write-up on how to apply Tensorlake dynamic network policies to long-running, stateful AI workloads. AI agents usually don’t need the same network access throughout an entire workflow. They may need one trusted source during context retrieval, another service
Secure AI Agents with Tensorlake Dynamic Network Policies
From pub.towardsai.net