Namespace vs Tensorlake Sandboxes
Choose Namespace for teams that want macOS, Windows and Linux VMs for agents and CI from one SDK, plus persistent Devboxes for coding agents; choose Tensorlake Sandboxes for agent harnesses, RL rollouts and coding agents that need memory snapshots, cloning and warm pools at scale. Namespace uses KVM virtual machine isolation; Tensorlake Sandboxes uses MicroVM (gVisor for GPU) isolation and is open source.
Key differences between Namespace and Tensorlake Sandboxes
- Isolation: Namespace uses KVM virtual machine; Tensorlake Sandboxes uses MicroVM (gVisor for GPU).
- Open source: Tensorlake Sandboxes is open source (Apache-2.0); Namespace is not.
- Session length: Deadline-based; Devbox 3-24 h (Namespace) versus 2 h / 24 h / unlimited (Pro) (Tensorlake Sandboxes).
- SDKs and interfaces: Only Namespace lists Go, MCP server and gRPC/Connect API. Only Tensorlake Sandboxes lists Python, Rust and REST API.
What they have in common
- Both are hosted platforms.
- Both support snapshots.
- Both can pause and resume a sandbox.
- Both list TypeScript and CLI.
Namespace vs Tensorlake Sandboxes at a glance
| Attribute | Namespace | Tensorlake Sandboxes |
|---|---|---|
| What it is | Isolated Linux, macOS and Windows VM instances and persistent Devboxes on a developer-compute cloud, with an SDK, egress policy and SOC 2 Type II. | MicroVM sandboxes with memory snapshots, copy-on-the-fly cloning, warm pools and egress policy, alongside hosted Git and a versioned filesystem, with an Apache-2.0 runtime and BYOC on AWS. |
| Type | Hosted platform | Hosted platform |
| Isolation | Hypervisor-backed VM instances with KVM (nested virtualisation on amd64 Linux); the homepage names a custom hypervisor and scheduler but gives no further detail | MicroVM per sandbox using hardware virtualisation (hosts must expose /dev/kvm); hypervisor not named; GPU sandboxes run on gVisor instead |
| Open source | No | Yes (Apache-2.0) |
| Self-host / BYOC | Not documented / Not documented | Yes / Yes |
| SDKs | JavaScript/TypeScript, Go, CLI, MCP server, gRPC/Connect API | Python, JavaScript/TypeScript, Rust, CLI, REST API |
| Cold start (vendor claim) | Not documented | Docs: CPU microVMs "boot in hundreds of milliseconds"; homepage cites the vendor's own SQLite benchmark with an 84 ms cold start and about one second to suspend or resume (vendor claims) |
| Max session | Compute instances run to a deadline you set and can extend; no maximum stated. Devboxes auto-shut down on idle (15 min to 8 h presets) with a plan maximum of 3 hours (Developer, Devbox Plus), 5 hours (Team) or 24 hours (Business), raisable to 24 hours via support | Idle timeout (default 600 s), not a wall-clock cap; plan maximums are 2 hours (Free), 24 hours (Usage Credits) and unlimited (Pro, Enterprise); named sandboxes suspend on timeout, ephemeral ones terminate |
| Persistence | Compute instances can be suspended (RAM and disks snapshotted) and woken; volumes and snapshots are managed via the SDK; Devboxes keep persistent storage across stop and start | Named sandboxes suspend and resume with memory and filesystem intact; filesystem or memory snapshots (checkpoints) persist after termination and can be restored with different resources; copy clones a running or suspended sandbox, including memory and processes, into one or many warm-started sandboxes; terminated sandboxes can be restarted under the same ID for 48 hours |
| Snapshots / pause | Yes / Yes | Yes / Yes |
| GPU | Not mentioned on the compute, machine-shape or pricing pages | Yes, by request only: H100 GPU sandboxes on gVisor at $3.95 per GPU-hour (reserved), with no live resizing or Tensorlake filesystem mounts |
| Networking | Egress policies with ALLOW rules in BLOCK or ADVISORY mode, header INJECT of vault secrets and PROXY rules via deep packet inspection, applied to runners, Devboxes and Compute API instances; private networking between instances in a workspace; federation to your own cloud | Outbound open by default; allow_out turns the sandbox default-deny (domains, wildcard subdomains, IPv4, CIDRs) and deny_out overrides it; policy can be changed at runtime; inbound only to ports listed in exposed_ports, authenticated unless explicitly opened; shared NAT egress IPs for allow-listing; SSH over WebSocket PTY and port tunnels |
| Pricing | Compute "unit minutes" = vCPU (or RAM/2 if higher) x minutes x platform multiplier (Linux 1, Windows 2, Linux on Apple Silicon 7, macOS 10) at $0.001 prepaid or $0.0015 overage per unit minute, 1-minute minimum; e.g. 1 vCPU/2 GB Linux $0.001/min. Plans: Developer $0 pay as you go, Team $100/month (100,000 unit minutes), Business $250/month (250,000), Devbox Plus $250/month (50,000 Devbox Minutes + 400 GB-month). Devboxes $0.004 per Devbox Minute (Linux S=1, M=2, L=4, XL=8 per minute; macOS M=15, L=30) plus $0.20/GB-month storage | Usage Credits / Pro per second: active CPU $0.07 / $0.042 per core-hour (minimum 20% of allocated vCPU), RAM $0.015 / $0.009 per GB-hour, root disk $0.0002 / $0.0001 per GB-hour, snapshot storage $0.07 per GB-month while suspended; egress free. Usage Credits are prepaid packs from $5 (1 CU = $0.01); Pro is $250/month including 25,000 CU with $0.01/CU overage; Enterprise custom |
| Free tier | 30-day free trial of the Developer plan; no card required at signup; no permanent free allowance stated | Free plan: 1 concurrent sandbox, 1 vCPU/1 GB/10 GB, sessions up to 2 hours |
| Compliance | SOC 2 Type II; report and sub-processors via trust.namespace.so; regional preferences on all plans and region-exclusive residency on Enterprise | Homepage and docs claim SOC 2 Type II and HIPAA; EU data residency and zero data retention are listed on the docs index |
| Regions | Multiple regions worldwide, not individually listed; the demo shows us-east and placement can be constrained by continent or site | Not listed; the docs mention EU data residency and BYOC into your own AWS account |
| Company headquarters | Not documented | San Francisco, California, United States |
| Good fit for | Teams that want macOS, Windows and Linux VMs for agents and CI from one SDK, plus persistent Devboxes for coding agents | Agent harnesses, RL rollouts and coding agents that need memory snapshots, cloning and warm pools at scale |
Verified November 14, 2026 from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose Namespace
- You need macOS or Windows VMs for agents, not only Linux
- You want one platform for CI runners, builds and agent compute with shared caches
- You need SOC 2 Type II and data-residency controls
- You want persistent Devboxes that agents and humans share over SSH and IDEs
Reasons to choose Tensorlake Sandboxes
- You need memory snapshots and cloning of running sandboxes for parallel agents or RL rollouts
- You want warm pools and queued creation for bursty, high-concurrency workloads
- You need to run the sandbox data plane inside your own AWS account
- You want hosted Git and a versioned filesystem next to the sandbox
Trade-offs to check first
- Namespace: Devbox sessions are capped at 3 to 24 hours depending on plan
- Namespace: Billing has a 1-minute minimum and platform multipliers (Windows 2x, macOS 10x Linux)
- Tensorlake Sandboxes: Hypervisor is not named in the docs
- Tensorlake Sandboxes: GPU sandboxes are by request only and use gVisor rather than a VM
Both are worth piloting with your own image and region. See the full Namespace profile and Tensorlake Sandboxes profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Namespace or Tensorlake Sandboxes better for AI agents?
What is the difference between Namespace and Tensorlake Sandboxes?
Which is open source, Namespace or Tensorlake Sandboxes?
How do Namespace and Tensorlake Sandboxes isolate code?
How does Namespace pricing compare with Tensorlake Sandboxes?
Do Namespace and Tensorlake Sandboxes support GPUs?
Can you self-host Namespace or Tensorlake Sandboxes?
How long can sessions run on Namespace and Tensorlake Sandboxes?
Do Namespace and Tensorlake Sandboxes support snapshots or pause and resume?
Sources
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 14, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). Namespace vs Tensorlake Sandboxes. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/namespace-vs-tensorlake/