Tensorlake vs Claude Managed Agents
Tensorlake sells sandboxes: Firecracker microVMs you create through an API and fill with your own agent, with memory snapshots and warm clones. Claude Managed Agents sells the agent itself: you send Claude a task, and Anthropic's harness runs it in a container Anthropic manages, or runs its tools on a worker you host.
The companies and products
Tensorlake
Tensorlake is a San Francisco company that sells infrastructure for AI agents, with sandboxes as its main product.
Tensorlake Sandboxes are Firecracker microVMs that you create through an API and that boot in a few hundred milliseconds. CPU sandboxes have /dev/kvm, can resize CPU and memory while they run, and can suspend with their memory and running processes. You can copy a running sandbox into several warm clones. Around them Tensorlake sells pre-warmed pools, versioned Cloud Volumes, hosted Git and a bring-your-own-cloud option, aimed at teams running coding agents, evals and RL rollouts.
- Headquarters
- San Francisco
- Investors shown
- Redpoint and Amplify Partners
Claude Managed Agents
Claude Managed Agents is Anthropic's ready-made agent harness: Claude runs as an autonomous agent, and you talk to it through an events API.
This is an agent platform, not a sandbox you rent. You define an agent (model, prompt, tools, MCP servers, skills) and an environment, then start sessions, send messages as events and stream back what Claude does. The harness handles tool calls, prompt caching and compaction. Each session gets its own Ubuntu container in Anthropic's cloud, or runs its tools on a worker that you host. It is built for teams that want Claude to do long tasks without building their own agent loop or sandbox.
Which use cases each one fits
For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “8th cheapest of 365” means 7 of the other 364 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.
| Use case and its workload | Tensorlake: price rank | Claude Managed Agents: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Tensorlake and boat both fit a software factory, and both expose /dev/kvm for emulators; boat ranks 5th and Tensorlake 8th in our table. A Managed Agents cloud sandbox with up to 8 GB of memory is a compromise; a self-hosted worker can be bigger, on a host you run. | 8th cheapest of 365 $1,315 a month | 139th of 365, with limits $964 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Managed Agents lets an idle agent sleep with no runtime charge and wake on the next message; cloud sandbox files are kept 30 days after creation. Tensorlake keeps a named sandbox's memory while it sleeps. boat keeps the disk and has no session cap once auto-stop is off (default 1 hour). | 14th cheapest of 361 $1,730 a month | 259th of 361, with limits $2,511 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Tensorlake ranks 29th in our table and fits many short runs well. Managed Agents bills runtime only while the agent works. boat's start limits make big bursts a compromise. | 29th cheapest of 336 $250 a month | 167th of 336, with limits $756 a month | 189th of 336, with limits $2,000 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month boat ranks 3rd and Tensorlake 13th in our table, since both let your users open what runs inside. A Managed Agents cloud sandbox has no documented inbound ports; with a self-hosted worker you open ports on your own host. | 13th cheapest of 349 $561 a month | 227th of 349, with limits $823 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month Tensorlake ranks 2nd of 349 providers for RL rollouts in our table, with up to 1,000 sandboxes at once on Pro and warm clones from one state. Managed Agents is a compromise here. | 2nd cheapest of 349 $5,637 a month | 247th of 349, with limits $3,978 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 35th cheapest of 359 $506 a month | 247th of 359, with limits $320 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month boat ranks 2nd for CI in our table. Tensorlake fits too. The Managed Agents cloud sandbox lists Docker as limited availability. | 53rd cheapest of 374 $424 a month | 228th of 374, with limits $96 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB boat ranks 19th for an all-day dev box in our table. Tensorlake is built around suspending idle sandboxes, after 10 minutes by default unless you raise the timeout. The Managed Agents cloud sandbox has no documented SSH. | 202nd of 371, with limits $250 a month | 238th of 371, with limits $48 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Tensorlake has an XFCE desktop with screenshot, mouse and keyboard calls. Managed Agents ships headless Chromium; you add a desktop through custom tools, MCP or a self-hosted worker. boat streams a built-in desktop at 60 fps. | 10th cheapest of 367 $387 a month | 166th of 367, with limits $288 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 12th cheapest of 356 $250 a month | 181st of 356, with limits $288 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 25th cheapest of 343 $250 a month | 194th of 343, with limits $390 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 123rd of 327, with limits $3,484 a month | 153rd of 327, with limits $4,798 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 8th cheapest of 351 $250 a month | 219th of 351, with limits $160 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Tensorlake | Claude Managed Agents | boat |
|---|---|---|---|
| What it is | A sandbox platform: you create microVMs through an API and run your own agent inside | A hosted Claude agent: Anthropic's harness runs Claude, and tools run in a cloud sandbox or on a worker you host | A sandbox platform: each agent gets its own full Linux VM, with coding agents installed |
| Isolation | Firecracker microVMs with their own kernel; GPU sandboxes use gVisor | Cloud sandbox: isolated Linux container per session. Self-hosted worker: the isolation of the host you run | Full VM with its own kernel on hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared |
| Machine size | Up to 16 vCPU, 64 GB RAM and 100 GB disk on Pro; CPU and memory resize while running | Cloud sandbox: up to 8 GB memory and 10 GB disk, vCPU not published, not configurable. Self-hosted worker: whatever your host has | 2 to 16 vCPU and 4 to 32 GB, disk 51 to 251 GB; 16 vCPU needs the $100 plan or higher |
| Docker and /dev/kvm | Docker on the tensorlake/ubuntu-systemd image; /dev/kvm in CPU sandboxes | Cloud sandbox: Docker listed as limited availability; root, systemd and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm on every sandbox |
| Memory snapshots | Yes: suspend and memory snapshots keep running processes and restore warm | No: the sandbox's files and packages are checkpointed when a session goes idle | No: the disk is saved every minute and at each stop; a resume is like a reboot |
| Clone or fork | Copy a running or suspended sandbox into many warm clones with memory | No documented fork or clone of a session or sandbox | Fork a running sandbox from its last 1-minute disk snapshot |
| Idle and wake | Idle timeout, 600 s by default, then suspend (named sandboxes) or terminate | An idle session has no runtime charge and resumes from its checkpoint on the next message | Auto-stop 1 h after creation or resume by default (up to 30 days, or off on paid plans); it does not watch for idle; a stopped sandbox is resumed by API |
| How long state lasts | Named sandboxes keep memory while suspended, billed as snapshot storage; Cloud Volumes keep files across sandboxes | Cloud sandbox files are kept 30 days after creation; history, memory stores and outputs stay until you delete them | Disk kept at least 14 days after a stop; saved snapshots have no scheduled expiry |
| Agents | You install your own agent; managed images are plain OS bases | Anthropic's harness with Claude models, with steering, memory stores, multiagent threads, budgets and webhooks | Seven harnesses installed (Claude Code, Codex, OpenCode and more), driven from outside with a prompt, steer and events API |
| API keys | Stored secrets are injected into the sandbox as environment variables | Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host | Optional AI credentials proxy ($1 a day while on, plus $1 per 1,000 requests); with it on, real keys of supported providers stay outside; other secrets still enter |
| Inbound traffic | HTTP, WebSocket and gRPC on exposed ports (public or authenticated), SSH, and raw TCP through authenticated client tunnels; no dedicated IP | Cloud sandbox: no documented inbound ports or SSH; reached through the sessions and events API. Self-hosted worker: the ports you open | Up to 50 HTTPS URLs, token-gated by default; SSH; raw ports on a public IPv6 address; no dedicated IPv4 |
| Desktop and browser | ubuntu-vnc image: XFCE desktop with Firefox over VNC, with screenshot, mouse and keyboard calls | Headless Chromium with Playwright; add a desktop through custom tools, MCP or a self-hosted worker | Built-in desktop and Chrome streamed at 1920x1080, 60 fps, with computer tools |
| Outbound rules | allow_out and deny_out lists by domain, IP or CIDR, or no internet at all | Unrestricted, or limited to listed hosts plus optional package registries and MCP servers | No provider-side allowlist; you set your own firewall as root |
| Where it runs | Managed cloud with EU data residency supported (no region list published), or your own cloud through BYOC | US workspace geo only, or tools on workers you host yourself | Germany, Finland and France; you cannot pick one; no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Tensorlake | Claude Managed Agents | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No documented way | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | Yes | No documented way | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | Yes | No documented way | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No documented way | Yes |
| SSH | Yes | No documented way | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | No documented way | Yes |
| Live fork (no pause) | Yes | No documented way | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | Yes | No documented way |
| HTTPS preview URLs | Yes | No documented way | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | Yes | No documented way |
| Secret proxy | No documented way | Yes | Yes |
| Secret proxy for any API | No documented way | Yes | Yes |
| Preinstalled agents | No documented way | Yes | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | No documented way | Yes | No documented way |
| GPU | Yes | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | Yes | No documented way |
| BYOC | Yes | Yes | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No documented way | Yes | Yes |
| Audit logs | Not published | Not published | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Yes | No documented way | No documented way |
| EU data residency | Yes | No documented way | No documented way |
| Zero data retention | Yes | No documented way | Yes |
Performance
Tensorlake and Claude Managed Agents are not in StarSling's CPU benchmark, so we cannot say which is faster, and Anthropic does not publish how many vCPUs a cloud sandbox gets. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. In ComputeSDK's run of 6 November 2026, Tensorlake started 100 sandboxes at once with a median of 1.55 s to first command, at its default size.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Tensorlake and Claude Managed Agents are not in the public benchmarks we use, so we cannot say which is faster.
Pricing in five scenarios
Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | Tensorlake, a month | Claude Managed Agents, a month | boat, a month |
|---|---|---|---|
| One coding agent, workdays 4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days | $250 · Pro | $13 · Claude API (pay-as-you-go, usage tiers) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $250 · Pro | $53 · Claude API (pay-as-you-go, usage tiers) · with limits | $26 · $20/mo |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $1,030 · Pro | $634 · Claude API (pay-as-you-go, usage tiers) · with limits | $317 · $20/mo × 3 seats |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $293 · Pro | $360 · Claude API (pay-as-you-go, usage tiers) · with limits | $200 · $100/mo × 2 seats |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $1,127 · Pro | $796 · Claude API (pay-as-you-go, usage tiers) · with limits | $8,800 · $2000/mo · with limits |
Tensorlake: Pro is $250 per billing cycle, which includes 25,000 CU ($250) of usage, then $0.01 per CU. CPU is billed on active execution, with a minimum of 20% of allocated vCPU. RAM and disk bill on allocation while the sandbox runs, and a suspended sandbox pays $0.07 per GB-month of snapshot storage.
Tensorlake: Small users can buy prepaid Usage Credits packs of $5, $10 or $20 at higher rates instead; sandboxes stop when the balance hits zero. A free plan runs 1 sandbox of 1 vCPU / 1 GB for up to 2 hours. The table prices the Pro path, so it overstates very small workloads.
Claude Managed Agents: Managed Agents bills model tokens at API list rates plus $0.08 per session-hour of runtime, metered only while the session is running, including time spent waiting on the model. The table shows runtime only, and the sandbox size is not published, so it is not a like-for-like machine. Tokens come on top. A self-hosted worker adds the cost of your own host.
Claude Managed Agents: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month; unused time does not carry over. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge, and boat keeps its disk for at least 14 days. Saved snapshots above the included count and the optional AI credentials proxy still charge while sandboxes are stopped. Model tokens for the built-in agents are paid to your model provider.
Limits in those scenarios
No scenario counts as a clean fit for Managed Agents in our table: its cloud sandbox has up to 8 GB of memory and 10 GB of disk, an unpublished vCPU count and Docker in limited availability. Anthropic publishes no concurrent-session cap, only 300 creates a minute and usage-tier spend caps. A self-hosted worker removes the size limits, on a host you run. Tensorlake fits all five scenarios on Pro, which allows 1,000 sandboxes at once; an ephemeral sandbox ends after 10 idle minutes by default. boat fits four: the $2,000 plan includes 90 starts a minute, and starts above 270 a minute fail with 429, so 1,000 short jobs at once does not fit. A boat resume is like a reboot, and a machine failure loses the writes after the last 1-minute snapshot.
| Scenario | Tensorlake | Claude Managed Agents | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario |
| None for this scenario |
| One agent that never stops | None for this scenario |
| None for this scenario |
| 50 agents in parallel | None for this scenario |
| None for this scenario |
| Sandboxes for your users | None for this scenario |
| None for this scenario |
| 1,000 short jobs at once | None for this scenario |
|
|
Which one should you use?
Use Tensorlake when
you run your own agent across many short sandboxes at once, need memory snapshots and warm clones, or want GPUs or your own cloud account.
- Memory snapshots and warm clones. Useful when agents must resume mid-process: Tensorlake saves a sandbox's memory and copies it into many warm clones.
- Big fan-outs of any agent. Teams running RL rollouts or evals with their own agent can run up to 1,000 sandboxes at once on Pro.
- GPUs, /dev/kvm or your cloud. Tensorlake offers GPU sandboxes by request, /dev/kvm in CPU sandboxes, and BYOC on AWS, GCP, Azure and more.
Use Claude Managed Agents when
you want Claude itself to do long tasks with no harness to build, idle time with no runtime charge, and the option to run tools on your own workers.
- No agent loop to build. Teams that want Claude doing long tasks get the harness, caching, compaction, memory and webhooks ready to use.
- Idle sessions sleep with no runtime charge. Agents that wait a long time between messages pay runtime only while working, and resume on the next message.
- Tools on your own workers. Teams with strict network rules can limit sandboxes to listed hosts, or run every tool call on their own infrastructure.
Where boat fits
If your agents do steady work for hours, like installs, builds, tests, Docker and emulators, look at boat. It gives each agent a full VM that you can open from outside, with Claude Code, Codex and other agents installed. boat has no memory snapshots, no GPU and no region outside Europe.
A whole VM, no worker to run
A Managed Agents cloud sandbox has up to 8 GB of memory and Docker in limited availability; a bigger self-hosted worker is a host you run and pay for. boat gives up to 16 vCPU with root, Docker, systemd and /dev/kvm.
Open what the agent builds
A Managed Agents cloud sandbox has no documented inbound ports or SSH. Tensorlake reaches raw TCP only through authenticated client tunnels. boat gives up to 50 HTTPS URLs, token-gated by default, SSH and raw ports on a public IPv6 address.
Any agent, ready to run
On Tensorlake you install the agent harness yourself, and secrets are injected into the sandbox. Managed Agents runs Anthropic's harness with Claude models. boat installs seven agents, including Claude Code and Codex, so you can try both on the same task.
Use boat when your agents need a full machine with no setup: Docker, emulators, a desktop, ports you can open, a disk kept between runs, and the choice of Claude Code, Codex or other agents. Compare it one to one: boat vs Tensorlake and boat vs Claude Managed Agents.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is Tensorlake cheaper than Claude Managed Agents?
For runtime alone, Managed Agents costs less in four of the five scenarios we price, for example $634 against $1,030 for 50 agents in parallel. Tensorlake costs less for sandboxes for your users ($293 against $360). Managed Agents adds model tokens on top, and its cloud sandbox is not a clean fit for any scenario. boat is $317 and $200 for those two.
Which is faster, Tensorlake or Claude Managed Agents?
We cannot say: neither is in StarSling's CPU benchmark, and Anthropic does not publish its sandbox vCPU count. boat did 28.06 V8 Web Tooling runs/s, second of 15 in StarSling's run of 3 October 2026, on a Ryzen 9 9950X host.
Can Tensorlake and Claude Managed Agents run Docker?
Tensorlake runs Docker on its tensorlake/ubuntu-systemd image, and its CPU sandboxes have /dev/kvm. The Managed Agents cloud sandbox lists Docker as limited availability; a self-hosted worker runs what your host runs. boat gives root, Docker, systemd and /dev/kvm in every VM.
Can I run Claude Code on either one?
Managed Agents runs Anthropic's own harness with Claude models; its docs do not describe the Claude Code CLI as a session harness. On Tensorlake you install and wire up your own agent. boat ships Claude Code, Codex and other agents installed.
Which one keeps an agent's state between sessions?
Tensorlake's named sandboxes suspend with memory and running processes. Managed Agents checkpoints files when a session goes idle and keeps them 30 days after the sandbox is created; history and memory stores stay until you delete them. boat saves the disk every minute and at each stop, keeps a stopped disk at least 14 days, and a saved snapshot has no scheduled expiry.
Is boat SOC 2 compliant?
No. SOC 2 is in progress, and boat has no SOC 2 report or HIPAA BAA today. Live status is at status.ascii.dev and the data retention policy at docs.boat.dev/data-retention.
Try boat
Install the CLI, then run boat new.
7-day free trial