Agentic Index
boxd vs exe.dev (2026)
Both vendors last verified
Both sell persistent Linux machines for agents that you reach over SSH, with integrations whose secrets never enter the machine, and they differ in how machines are billed and how they idle. boxd bills each machine per second in euros, hibernates it after four idle hours and wakes it on the next request with its processes intact, forks a running machine with its memory in under 200ms, and ships Claude Code, Codex and OpenCode with a live desktop where an agent drives a browser. exe.dev sells a monthly pool of CPU and memory, from $15 a month for 2 vCPUs and 4 GiB, that runs as many always on VMs as fit, with more than a hundred integrations injected at its edge, an LLM gateway, email in and out for each VM, and Shelley, its own web coding agent with a browser tool. exe.dev offers eight regions to new accounts and team single sign on through Google or OIDC, while boxd runs in Frankfurt or New York and self hosts free up to 16 vCPUs. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Choose boxd when agents need forks that keep memory and per second billing, and exe.dev when a flat monthly pool of always on VMs with a choice of region fits better.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. boxd and exe.dev are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,165 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose boxd if
- Forks should copy a running machine with its memory, so an agent can branch a task or a rollout from a warm state.
- Idle machines should hibernate and stop compute charges, then wake on the next request with processes intact.
- Claude Code, Codex and OpenCode should come preinstalled, rather than a vendor's own agent.
- Automations written in TypeScript should run on schedules and integration events.
- You want to self host the same release free up to 16 vCPUs, including air gapped installs.
Choose exe.dev if
- A flat monthly fee for a pool of CPU and memory should cover dozens of VMs, from $15 a month.
- VMs should run in one of eight regions open to new accounts, from Los Angeles and Frankfurt to Tokyo and Sydney.
- Each agent should have its own email address to receive and reply to messages.
- Teams should enforce sign in through Google or an OIDC provider such as Okta, with unlimited users on Work.
- A web and mobile coding agent should be running on every VM from the start, with models from an LLM gateway.
| Feature | b boxd |
e exe.dev |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
boxdIntegrations & Tool Calling Agents on a machine act in outside systems through 128 integrations, including GitHub, Linear, Slack, Notion, Jira, Salesforce, HubSpot, Stripe and Zendesk, each with typed tools such as creating an issue or sending a message. A person connects an account once through the provider's consent screen, personally or as a shared connection for the whole organization, and the platform then makes each call on the machine's behalf, so the credential never enters the machine. The in machine run CLI and the @boxd/run SDK call these tools, and scripts reach any other API, database or cloud account with ordinary libraries. Sourcedocs.boxd.sh/guides/integrations/connectionsread 2026-11-05 |
||
|
exe.devIntegrations & Tool Calling Agents use outside services through integrations whose secrets stay on exe.dev's servers and are added to requests at the network edge, so the VM can call the service but cannot read the key. Built in types cover GitHub, Slack and Slack bots, Discord and Discord bots, S3 compatible storage, LLM providers, calls between VMs and tunnels to private networks, the catalog covers more than a hundred services, Google Calendar and Gmail let an agent add events and send email as the user, and workload identity federation covers AWS, Google Cloud, Anthropic, OpenAI and Tailscale. Integrations attach to VMs directly, by tag or to every VM. Sourceexe.dev/docs/integrationsread 2026-11-05 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
boxdWorkflow Orchestration Background jobs give automations a managed lifecycle. A script that registers a schedule or trigger runs as a job that survives reboots, waits for a missing connection instead of failing, and restarts with exponential backoff for up to five attempts before it is marked failed. boxd's fan out pattern has a coordinator create one machine per worker, run a coding agent headless in each and let a lead agent merge the reports, and a fork brings a machine's jobs along paused so nothing runs twice. The sequencing, branching and hand offs in that pattern are code the customer writes against the SDK, and boxd has no workflow graph, step model or multi agent runtime of its own. Sourcedocs.boxd.sh/guides/automations/jobsread 2026-11-05 |
||
|
exe.devWorkflow Orchestration There is no workflow logic for an agent's steps. Shelley can run several conversations at once on one VM or across VMs, each its own session, and pools share capacity across VMs, but sequencing, branching and retrying work stay in the agent or the customer's code. Sourceexe.dev/docs/shelley/uniqueread 2026-11-05 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
boxdTriggers & Channel Coverage Work reaches a machine on schedules, events and inbound requests. An automation registers durations or cron expressions with every() and subscribes to integration events with .on(), such as a new Linear issue or a pull request through the boxd GitHub App, and 36 integrations emit triggers. The platform holds the next due time and wakes a hibernated machine shortly before it, holds events that arrive while a machine wakes for up to 15 minutes, and fires a missed cron slot once on wake. A hibernated machine also wakes on the next HTTPS request, so an agent served from it answers webhooks at its own address. Sourcedocs.boxd.sh/guides/automations/scriptsread 2026-11-05 |
||
|
exe.devTriggers & Channel Coverage Work can reach an agent on its own. A VM can receive email at its own address, delivered to a mailbox the agent watches, and reply within each sender's thread, and Slack and Discord bot integrations carry messages both ways. VMs stay running, so an agent on one can act on incoming mail, chat messages or requests to its public HTTPS address as they arrive. There is no built in scheduler. Sourceexe.dev/docs/receive-emailread 2026-11-05 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
boxdKnowledge Grounding & RAG No retrieval index, vector store or knowledge base over the customer's content comes with the platform. Files on a machine's disk, standalone disks that outlive a machine and data sets saved into a snapshot are storage the agent's code reads, not an index a query returns. Tools such as Notion, Confluence or Google Drive are searched through their own integrations, and any grounding layer is something the customer installs on the machine. Sourcedocs.boxd.sh/llms.txtread 2026-11-05 |
||
|
exe.devKnowledge Grounding & RAG No retrieval index or knowledge base over the customer's content comes with the platform. Files an agent reads live on the VM's disk or in attached storage, and Shelley reads project instructions from an AGENTS.md file. Sourceexe.dev/docsread 2026-11-05 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
boxdMemory & State Persistence Machines keep their working state between sessions. A machine on standby resumes in under a millisecond and a hibernated one wakes with its memory and processes intact, and coding agent sessions live on the persistent disk, so a job delegated in the morning can be resumed interactively later. Forks, checkpoints and snapshots copy or rewind that state. Automations also get object(name), a named JSON store written on every assignment and restored on the next run, meant for cursors, dedup sets and counters. All of it is machine and script state the developer manages, with no memory layer of stated scope and lifetime that a buyer can review, edit or delete as memory. Sourcedocs.boxd.sh/guides/automations/scriptsread 2026-11-05 |
||
|
exe.devMemory & State Persistence An agent's working state lasts because the computer does. VMs are long lived with persistent NVMe disks whose changes are streamed to other machines in the region, and they can be backed up and copied. Shelley keeps each conversation as a log and compacts older context into new generations so long work can continue. This is machine and conversation state the user manages, not a memory layer of stated scope that can be reviewed or deleted as memory. Sourceexe.dev/docs/what-is-exeread 2026-11-05 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
boxdHuman Oversight & Guardrails A person can step into an agent's work while it runs. Every machine has a live desktop in the browser where its owner watches the agent's browser, takes over the keyboard to enter a password, solve a captcha or fix a form, and hands control back without stopping the agent. The preinstalled coding agents are told to share that desktop link whenever they need someone, so a login or approval happens in the browser the agent already opened. There is no approval gate, pause primitive or policy that holds an agent's action until a person reviews it. Sourcedocs.boxd.sh/guides/desktopread 2026-11-05 |
||
|
exe.devHuman Oversight & Guardrails No approval step, consent checkpoint or escalation to a person comes with Shelley or with agents on a VM. Egress set to integrations only, private HTTPS addresses and secrets the VM cannot read limit what an agent can reach, but nothing holds an action until someone reviews it. Sourceexe.dev/docs/internet-accessread 2026-11-05 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
boxdSecurity, Identity & Governance Organizations have three roles. Members use shared machines and create org billed ones, admins also invite and remove members, change roles, set defaults, create teams and revoke org API keys, and the single owner can demote admins. Admin invites need an interactive login, so an API key or a token minted inside a machine cannot send one. People sign in with GitHub or Google, with SAML single sign on offered to enterprise customers on request. A DPA is available, and SOC 2 Type II and ISO 27001 are both in progress, not held. Each machine is a KVM microVM with its own kernel, and egress allowlists and host bound secrets are enforced on the host, outside the machine. Sourcedocs.boxd.sh/guides/organizationsread 2026-11-05 |
||
|
exe.devSecurity, Identity & Governance Teams have a billing owner, admins who manage members and can reach any member's VM, and users who manage their own VMs, and a team can require sign in through Google or a custom OIDC provider such as Okta or Azure AD. API tokens carry an expiry and a set of allowed commands, SSH keys can be scoped to one VM, HTTPS addresses are private by default and integration secrets never reach the VM. exe.dev has no public compliance attestation, and its terms offer no certifications. Sourceexe.dev/docs/teams/overviewread 2026-11-05 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
boxdObservability & Auditability Automations are visible and the agent's own steps are not. The console's Automations page lists every background job with its triggers in plain English, the integrations it uses, its state, last run and last error, plus a generated write up and flow diagram for each script, and run logs prints or follows a job's log from inside the machine. Regional uptime and incidents appear on a public status page. A coding agent's prompts, tool calls and outputs are not traced by the platform, and no audit trail of member actions is offered. Sourcedocs.boxd.sh/guides/automations/jobsread 2026-11-05 |
||
|
exe.devObservability & Auditability Each VM can be inspected with resource metrics drawn as sparklines, and Shelley's web interface keeps every step of each conversation in view as it runs. No audit log, log service or traces for other agents on a VM come with the platform. Sourceexe.dev/apiread 2026-11-05 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
boxdDeployment & Data Residency Each machine runs in Frankfurt or New York, picked per machine from the CLI, console or SDK or set as an organization default, and its disk, memory, snapshots, checkpoints and backups stay in that region on Latitude.sh bare metal. Scale customers can have boxd operate the cluster inside their own cloud account, and the same release self hosts on AWS, Google Cloud or any KVM host, free up to 16 worker vCPUs and licensed above that, with air gapped installs supported. boxd gives conflicting accounts of its US region, with New York live in some places and coming soon with a waitlist in others. Sourcedocs.boxd.sh/guides/regionsread 2026-11-05 |
||
|
exe.devDeployment & Data Residency VMs run in a region chosen per account or per pool, among Los Angeles, New York, Dallas, Frankfurt, London, Tokyo, Singapore and Sydney, with Oregon closed to new accounts, while the main exe.dev server sits in the United States for everyone. Enterprise customers can have dedicated single tenant hardware or run their team's VMs on servers in their own cloud account or data center. Sourceexe.dev/docs/regionsread 2026-11-05 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
boxdPrebuilt Agents, Templates & Packs Machines arrive with Claude Code, Codex and OpenCode installed and configured through an instructions file that teaches each agent the platform, plus three preinstalled skills covering the in machine CLI, automations and the desktop, and a CLI skill for the laptop. Guides walk through development workspaces, preview environments, CI runners, personal assistants, sandboxes, agentic SaaS, RL environments and agent swarms, and connectors exist for open source tools such as TanStack AI, Pydantic AI, Harbor and Scale AI AgentEnv. These are configured third party agents and recipes a developer builds from, not prebuilt agents of boxd's own. Sourcedocs.boxd.sh/use-cases/coding-agentsread 2026-11-05 |
||
|
exe.devPrebuilt Agents, Templates & Packs The default VM image comes with Shelley, a general coding agent, already running, and VMs can start from custom Docker images. Repository buttons and deploy guides start projects on a VM. These are a starting agent and environments a developer works from, not a set of prebuilt agents for business tasks. Sourceexe.dev/docs/shelley/introread 2026-11-05 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
boxdModel Flexibility & Routing The customer decides which agents and models run. Claude Code and Codex use the customer's own subscription, signed in once and served to every private machine in the organization, or an API key stored as a secret, OpenCode signs in on each machine, and any other agent or model that runs on Linux can be installed. boxd adds no model of its own and does not route between providers, and it does not use customer data to train or improve any model. Sourcedocs.boxd.sh/use-cases/coding-agentsread 2026-11-05 |
||
|
exe.devModel Flexibility & Routing The customer chooses the models. The LLM integration routes requests by model ID to OpenAI, Anthropic, Fireworks or a custom HTTPS provider, using exe.dev managed credentials, the customer's own keys, a ChatGPT subscription or workload identity, and Shelley offers whichever models the attached integrations provide. Claude Code, Codex and other agents on the VM can point at the same gateway. Sourceexe.dev/docs/integrations-llmread 2026-11-05 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
boxdAPIs, SDKs & MCP Extensibility Outside code drives the platform through TypeScript and Python SDKs, a gRPC API whose full api.proto service definition is public for generating stubs in any language, and a CLI that returns JSON from its commands. Each region has its own API endpoint, and organization API keys keep working after the person who created them leaves. The SDKs cover machines, forks, snapshots, checkpoints, disks, egress, secrets, domains, organizations and teams, and a filesystem API reads and writes files inside a machine from code. Sourcedocs.boxd.sh/reference/grpc-apiread 2026-11-05 |
||
|
exe.devAPIs, SDKs & MCP Extensibility An HTTPS API runs the same command set as the SSH interface, covering VMs, sharing, resizing, tags, copies, pools, integrations and teams, with bearer tokens limited by expiry and allowed commands, and an explorer walks through each command. An MCP server at exe.dev/mcp connects Claude Code and other agents, with plugins for Claude and ChatGPT, though its tools are not enumerated publicly. Sourceexe.dev/docs/https-apiread 2026-11-05 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
boxdTesting, Debugging & Optimization There are no test cases, scoring or quality gates for an agent's behavior. The platform is where evaluations run, not how they are scored. Forks give every reinforcement learning rollout or benchmark trial a byte identical starting state, Moyai ran 279,577 Harbor benchmark machines on it, and a reproducibility check compares two forks run with the same seed, but rewards, datasets and scoring belong to the customer's own framework. Sourcedocs.boxd.sh/use-cases/reproducible-rl-environmentsread 2026-11-05 |
||
|
exe.devTesting, Debugging & Optimization There are no test cases, scoring or quality gates for an agent's behavior. Standalone VMs suit agent written code and CI jobs, with any testing done by the customer's own tools. Sourceexe.dev/docs/standalone-vmsread 2026-11-05 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
boxdBrowser & Computer Use Agents drive a real browser on the machine's own desktop. Every machine ships a browser automation CLI built for agents, backed by Chromium with anti bot fingerprinting and a persistent profile so logins stick, and scripts get the same browser through Playwright. A machine can also drive a Chrome window on the user's laptop over the DevTools protocol, for sites that only accept the user's own network, and the preinstalled agents get a browser tool for it automatically. Any GUI app installed on the machine opens on the same desktop. Sourcedocs.boxd.sh/guides/launch-a-browserread 2026-11-05 |
||
|
exe.devBrowser & Computer Use Shelley, the agent on the default image, has a browser tool that drives Chromium, navigating sites, taking screenshots and using browser profiles. Other agents on a VM get no browser of exe.dev's own and install and drive one themselves. Sourceexe.dev/docs/shelley/uniqueread 2026-11-05 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | b boxd |
e exe.dev |
|---|---|---|
|
Entry price Lowest public entry point |
Pay as you go with €30 of free credit, at €0.039 per active vCPU hour and €0.012 per GiB hour of memory in use. | Personal at $15 a month for a pool of 2 vCPUs and 4 GiB of memory with up to 50 VMs, after a 7 day free trial. |
|
Pricing confidence How public the numbers are |
Public, exact | Public, exact |
|
Billing Primary billing axis |
Per second active vCPU, memory in use and disk written | Monthly subscription for a shared pool of vCPU and memory, plus hourly metering for capacity beyond it |
|
Variable cost Workload / overage exposure |
High variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
No free tierTrial
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |
|
Pricing verified When this pricing was last checked |
exe.dev is run by Bold Software, Inc. of Berkeley and has no public compliance attestation. boxd's SOC 2 Type II and ISO 27001 certifications are still in progress, and boxd gives conflicting accounts of its US region. boxd prices in euros.
More comparisons with boxd or exe.dev
Other matchups in agent infrastructure platforms
Not the pairing you were after? These compare a different set of agent infrastructure platforms on the same 14 capabilities.