Blaxel vs AWS AgentCore
Blaxel is a sandbox company: each sandbox is a microVM, 4 vCPU or more, that sleeps seconds after you disconnect and wakes in under 25 ms with its memory. AWS AgentCore is an agent platform inside AWS, with 2 vCPU microVM sessions that stop after 8 hours, plus managed Code Interpreter and Browser tools.
The companies and products
Blaxel
Blaxel is a San Francisco company that runs cloud infrastructure for AI agents, and since September 2026 it is part of Baseten.
You get sandboxes, batch jobs, MCP server hosting and a model gateway. Each sandbox is a Firecracker microVM with its own kernel that drops to standby when nothing is connected and resumes in under 25 ms with its memory and running processes. It is built for agent products that start many sandboxes and want them asleep most of the time.
- Headquarters
- San Francisco, founded 2024
AWS AgentCore
Amazon Bedrock AgentCore is a set of AWS services to deploy and run AI agents: a Runtime that hosts your agent code, plus built-in Code Interpreter and Browser tools.
AgentCore is not a sandbox product first. It is a hyperscaler's agent platform: you push a container image or code, and each Runtime session gets its own Firecracker microVM that you reach through AgentCore APIs. Around it sit managed tools (Code Interpreter, Browser) and services for memory, identity, gateways and evaluations, and an Instances compute type runs longer sessions on EC2 in your own account. It is built for teams who already build on AWS and want agents to stay inside their account, IAM and VPC.
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. “10th cheapest of 367” means 9 of the other 366 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 | Blaxel: price rank | AWS AgentCore: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Blaxel fits a coding agent on a 4 vCPU sandbox with Docker, while AgentCore caps a microVM session at 2 vCPU and 8 hours; boat adds /dev/kvm and a disk that keeps everything. | 10th cheapest of 367 $2,373 a month | 100th of 367, with limits $888 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Blaxel's sleep and wake suits assistants that sit idle, while on AgentCore an assistant that lives all month outgrows the 8-hour lifecycle and needs Instances on EC2. | 12th cheapest of 366 $2,832 a month | 64th of 366, with limits $1,300 a month | 5th cheapest of 366 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Both fit well: AgentCore Code Interpreter bills only for CPU actually used, and Blaxel sandboxes sleep right after a run and resume in milliseconds. | 14th cheapest of 345 $144 a month | 7th cheapest of 345 $114 a month | 186th of 345, 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 Blaxel gives each sandbox a preview URL but its public tiers stop at 200 at once, and AgentCore sessions have no open ports; boat fits 300 users at once with HTTPS URLs on up to 50 ports. | 101st of 361, with limits $926 a month | 210th of 361, with limits $506 a month | Cheapest of 361 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 77th of 360, with limits $4,378 a month | 125th of 360, with limits $8,075 a month | 34th of 360, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month AgentCore fits evals as short managed sessions, while Blaxel's public tiers cap how many run at once at 200; boat starts a fresh VM per task from a named snapshot. | 136th of 364, with limits $704 a month | 33rd cheapest of 364 $650 a month | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month | 57th cheapest of 377 $431 a month | 52nd cheapest of 377 $399 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 265th of 368, with limits $114 a month | 228th of 368, with limits $52 a month | 18th cheapest of 368 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Blaxel runs a desktop and a browser, while AgentCore Browser drives a browser only; boat streams a full Linux desktop at 60fps. | 14th cheapest of 369 $634 a month | 104th of 369, with limits $202 a month | 6th cheapest of 369 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month AgentCore Browser is a managed Chromium with live view and session replay, a strong fit; Blaxel and boat run a browser inside the sandbox. | 16th cheapest of 367 $317 a month | 4th cheapest of 367 $144 a month | 7th cheapest of 367 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 16th cheapest of 346 $215 a month | 27th cheapest of 346 $287 a month | 6th cheapest of 346 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 147th of 338, with limits $4,292 a month | 165th of 338, with limits $5,458 a month | 71st of 338, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month Blaxel adds domain-level egress rules down to methods and paths, while AgentCore controls traffic with VPC security groups; boat gives root with raw TCP and nftables. | 3rd cheapest of 360 $217 a month | 62nd of 360, with limits $294 a month | 2nd cheapest of 360 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Can't run it | Can't run it | Can't run it |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Can't run it | Can't run it | Can't run it |
Key features
| Feature | Blaxel | AWS AgentCore | boat |
|---|---|---|---|
| What it is | A sandbox platform for agents: microVMs, batch jobs, MCP hosting and a model gateway | An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools | A sandbox platform: each agent gets its own full Linux machine |
| Isolation | Firecracker microVM per sandbox, own kernel | Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | 4 vCPU / 8 GB and larger; up to 256 GB of RAM on Custom | 2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Session length | No forced cap on an active sandbox; lower tiers delete sandboxes after 7 or 30 days | Up to 8 hours per lifecycle on microVMs, 15 idle minutes by default; up to 14 days on Instances | No cap on paid plans; you set the time to live |
| Sleep and wake | Standby seconds after the last connection, wakes in under 25 ms with memory and processes | Session stops when idle; the next call starts a fresh microVM | Stop keeps the disk and costs nothing; resume boots the VM again |
| What survives | Memory and files in standby; files live in memory (about half the RAM) unless you attach a volume | Only one storage mount under /mnt, up to 1 GB, in preview; EBS on Instances; the rest resets | The whole disk, saved every minute and on stop |
| Fork | Fork with memory and running processes (private preview) | No snapshots or fork of a session | Fork a running sandbox with its disk |
| Docker and /dev/kvm | Docker with a Docker-in-sandbox image; no /dev/kvm | Root in an arm64 container image; Docker and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Inbound access | Preview URL per port, public or token-protected; no SSH, raw TCP or public IP | No open ports or SSH; reached only through AgentCore APIs with IAM or JWT | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; SSH |
| Network controls | Domain allow and deny lists, method and path rules, static egress IPs | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet; filter inside the VM with nftables |
| Browser and desktop | Browser and desktop inside the sandbox | Managed Chromium with live view, recording and replay, profiles and proxies; no full desktop | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Coding agents | Claude Code image you drive from its terminal or your own harness | AWS's managed harness built on Strands Agents, or your own agent code | Claude Code, Codex and more preinstalled, driven from outside with a prompt, steer and events API |
| Keeping keys out | Proxy fills secrets into outbound HTTPS requests (public preview) | AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code | Credentials proxy for model providers and any HTTPS API; real keys never enter the sandbox |
| GPUs and regions | No GPUs; Oregon, North Virginia, London, Frankfurt | GPUs on Instances; 17 commercial AWS regions plus GovCloud | No GPUs; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Blaxel | AWS AgentCore | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | No | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | No | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | No | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | No | Yes | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Yes | Not published | Yes |
Performance
On the same Node.js build-and-test benchmark at 4 vCPU / 8 GB, boat did 26.69 runs per second and Blaxel 19.48, so boat does about 1.4 times the work in the same time. AWS AgentCore has no comparable measurement: it was not in the run, and its microVM sessions stop at 2 vCPU.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Blaxel measured on: Sandbox (active time, RAM-only pricing, CPU bundled). AWS AgentCore has no published run in this suite yet, so there is no like-for-like number to compare.
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.
| Scenario | Blaxel, a month | AWS AgentCore, 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 | $33 · Pay-as-you-go Tier 1 | $26 · Pay-as-you-go (Instances) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $120 · Pay-as-you-go Tier 1 | $107 · Pay-as-you-go (Instances) · 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 | $1,489 · Pay-as-you-go Tier 1 | $1,286 · Pay-as-you-go (Instances) · 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 | $396 · Pay-as-you-go Tier 2 · with limits | $423 · Pay-as-you-go · 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 | $876 · Pay-as-you-go Tier 2 · with limits | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Blaxel: Blaxel charges for allocated RAM per second while a sandbox is active, with CPU included. In standby you pay only snapshot storage, and volumes are billed on their full size.
AWS AgentCore: Runtime microVMs, Code Interpreter and Browser bill per second for CPU actually used and peak memory. The 4 vCPU shape in these scenarios is the Instances type: EC2 on-demand plus a 12% fee, with storage and data transfer on top.
AWS AgentCore: Plans start at $20 a month, and the whole fee is usage credit billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
On AgentCore, a 4 vCPU agent needs the Instances type, and files outside the storage mount reset on every stop, so none of the three long-running scenarios fits cleanly; the always-on one also hits the 14-day session cap. Blaxel fits those, but its self-serve tiers stop at 200 sandboxes at once, standby ones included, so 300 users or 1,000 jobs at once need a sales tier. AgentCore fits 1,000 short jobs at once, while boat queues starts above 90 per minute.
| Scenario | Blaxel | AWS AgentCore | boat |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Blaxel when
your sandboxes sit idle most of the time and must wake in milliseconds with their memory, on 4 vCPU or more, with preview URLs and egress rules.
- Sleeps in seconds, wakes in milliseconds. For sandboxes that sit idle, Blaxel sleeps seconds after the last connection and wakes in under 25 ms with its memory.
- A bigger machine with no 8-hour stop. A Blaxel sandbox can be 4 vCPU / 8 GB and has no forced session cap, where AgentCore microVMs stop at 2 vCPU and 8 hours.
- Preview URLs and fine egress rules. Each port can get a preview URL, and outbound traffic can be limited to chosen domains, methods and paths.
Use AWS AgentCore when
your agents must stay inside your AWS account and VPC, need a GPU, or are short code and browser tasks that fit the managed tools.
- It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC and PrivateLink, in 17 commercial regions plus GovCloud.
- Managed tools billed on CPU used. Code Interpreter and Browser are ready-made, bill CPU only while it is used, and Browser adds live view and replay.
- GPUs and two-week sessions on Instances. Agents that need a GPU or a session of up to 14 days can run on EC2 in your account.
Where boat fits
Blaxel is built for sandboxes that sleep most of the time, and AgentCore for agents that stay inside AWS. If your agents do hours of real work on one machine, with builds, Docker, emulators and an app you want to open, boat gives each one a whole Linux machine that keeps its disk.
A whole machine with /dev/kvm
Neither Blaxel nor AgentCore exposes /dev/kvm, so an Android emulator or a VM will not start, and AgentCore does not document Docker. boat runs Docker, systemd and nested virtualization in every sandbox, up to 16 vCPU.
A real disk that stays
Blaxel keeps files in memory, about half the RAM, unless you attach a volume at creation. AgentCore keeps only a 1 GB mount, so apt packages reset each stop. boat saves the whole disk every minute.
Ports, SSH and agents driven from outside
AgentCore has no open ports or SSH, and Blaxel has no native SSH or raw TCP. boat gives HTTPS on 50 ports, raw TCP and SSH, and drives Claude Code or Codex inside from outside with one API.
Use boat when your agents do real work for hours: builds, tests, Docker and emulators on a whole Linux machine with a disk that stays, a faster CPU and a URL you can open. Compare it one to one: boat vs Blaxel and boat vs AWS AgentCore.
Questions people ask
Is Blaxel cheaper than AWS AgentCore?
In the table AgentCore costs a little less for long-running agents, $26 against $33 for one coding agent on workdays, but it does not fit those scenarios because files outside its storage mount reset. For 1,000 short jobs at once Blaxel is lower ($876 against $1,615) but needs a sales tier to run that many. boat costs $20 a month for the workday agent.
Which is faster, Blaxel or AgentCore?
Blaxel did 19.48 runs per second on the Node.js benchmark at 4 vCPU / 8 GB, and AgentCore was not measured. boat did 26.69 on the same test.
Can Blaxel or AgentCore run Docker?
Blaxel runs Docker with its Docker-in-sandbox image. AgentCore runs your arm64 container image as root, but its docs do not say Docker works inside a session. Neither exposes /dev/kvm, which boat does.
How long can a session run?
A Blaxel sandbox has no forced session cap, though Tier 0 and 1 delete sandboxes after 7 or 30 days. An AgentCore microVM session lasts up to 8 hours, or 14 days on Instances. boat has no session cap on paid plans.
Do files survive a stop?
On Blaxel, standby keeps memory and files, and a volume keeps files beyond that. On AgentCore only a storage mount up to 1 GB, in preview, or EBS on Instances survives. boat keeps the whole disk and saves it every minute.
Where do they run?
Blaxel runs in Oregon, North Virginia, London and Frankfurt. AgentCore runs in 17 commercial AWS regions plus GovCloud. boat runs only in the EU, in Germany, Finland and France, with EU data residency.
Try boat
Install the CLI, then run boat new.
7-day free trial