Code & AI agent sandboxes: read the guide

smolvm

Open coreSandbox

Branchable microVMs for AI agents.

Homepage Docs Pricing Repository

Scanned 12 Oct 2026 · Schema v5 · features v21

From: $20/mo
Hosted plan fee plus metered base running time, active vCPU, RSS memory, used disk and egress. Standard $0, Pro $20/month, Startup $150/month, Enterprise custom. OSS engine free under Apache-2.0 plus own infrastructure.
Free tier: Not documented
Standard has $0 monthly plan fee and one-time $100 signup credit, no card. Pricing page + public JSON agree; cloud quickstart still says $10 monthly free usage, so recurring free credit is not treated as current.
Isolation: Virtual machine
hypervisor, or nothing at all
Regions: —
Country-level disclosure: Google Cloud US regions and data processed in United States. Exact hosted regions and placement choices not public; no multi-region availability inferred. Self-host placement is operator-defined.
Capabilities: 19 / 61
6 partial · 36 fail · 0 not assessed
Agent readiness: 10/11 · 9/11
read · drive, pre-login surface

Advertised for

Untrusted/generated code, persistent coding agent workspaces, warm branch fan out, portable dev/CI environments, Linux services, headless browsers; local Vulkan desktop/computer use and CUDA training/inference.

Built for

Developers, then technical

· CLI/API/SDK-first onboarding and code examples
· Own-kernel microVM, branch/checkpoint, egress and GPU terminology
· Usage-metered compute and memory pricing

01 Pricing Hosted plan fee plus metered base running time, active vCPU, RSS memory, used disk and egress. Standard $0, Pro $20/month, Startup $150/month, Enterprise custom. OSS engine free under Apache-2.0 plus own infrastructure.

Tier	Entrystandard	pro	startup	Topenterprise
Price	$0/month + usage	$20/month + usage	$150/month + usage	custom
Includes	20 machines; up to 8 vCPU/16 GB per machine; disk cap not published; idle apps scale to zero; one-time $100 signup credit, no card.	100 machines; up to 16 vCPU/24 GB/200 GB disk each; always-on apps; 99.95% uptime SLA.	1,000 machines; up to 32 vCPU/32 GB/200 GB disk each; priority support; always-on apps; 99.95% uptime SLA.	Contractual limits, dedicated nodes, volume rates, 99.95% SLA and SSO/SAML.
Transfer overage	$0.05/GB	$0.05/GB	$0.05/GB	—
vCPU hours overage	$0.05/h	$0.05/h	$0.05/h	—
Compute hours overage	$0.04/h	$0.04/h	$0.04/h	—
Memory gb hours overage	$0.0162/h	$0.0162/h	$0.0162/h	—

Free tier: Standard has $0 monthly plan fee and one-time $100 signup credit, no card. Pricing page + public JSON agree; cloud quickstart still says $10 monthly free usage, so recurring free credit is not treated as current.

Machine-hour $0.04 (1-minute minimum), active vCPU-hour $0.05, active memory GB-hour $0.0162, used disk GB-hour $0.0001, egress GB $0.05. Exec/file I/O $0.·Card required: unconfirmed·smolmachines.com

Overages: All usage is metered at published rates. Graduated 10% discount applies only to spend above $2,000/month; stopped machines billed only held used disk. Plan fee additional.

02 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Virtual machinehypervisor, or nothing at all

Persistence

Both local ephemeral runs and persistent machines. Cloud filesystem survives exec and stop/start; /tmp, /run and /dev/shm are memory-backed and reset on restart. Delete removes storage; stop is not a backup.

Snapshots / forks

Local live copy-on-write branches preserve RAM, processes and disks. Portable checkpoints and pause/resume are documented, with version/device/architecture constraints; current repo documents arm64 Mac-to-Linux restore and Windows checkpoints plus --freeze-source branches. Cloud branches are node-local; REST snapshots return 501, while separate checkpoint CLI routes are documented. Broad local/cloud live migration is not established.

Resources & limits

Storage

Persistent cloud machine filesystem sized by storageGb; memory-backed paths reset on stop. Local host-directory mounts and packed .smolmachine files. Cloud has no host mounts; generated legacy volume routes are not a supported storage API. No first-party object-storage service documented.

Limits & quotas

Local default 4 vCPU/8 GiB elastic RAM. Hosted Standard: 20 machines, 8 vCPU/16 GB per machine (disk cap unpublished); Pro: 100 machines, 16 vCPU/24 GB/200 GB; Startup: 1,000 machines, 32 vCPU/32 GB/200 GB; Enterprise contractual. Quota failures identify the plan limit. VM count is capacity/concurrency, not monthly sandbox-creation throughput.

GPU

Local/self-host only: Vulkan via virtio-gpu/Venus and CUDA API remoting over vsock. Needs compatible host graphics stack or NVIDIA GPU/driver. CUDA sharing is not hardware-partitioned GPU isolation. Cloud create API has no GPU resource fields; native Windows GPU acceleration unavailable.

Access

Deploy interface

clisdkapicontainer-imagetemplate

SDK languages

Node/TypeScript and Python smolmachines packages; embeddable Rust smolmachines crate. smol Machine API targets embedded local engine or cloud; older smolvm-sdk targets smolvm serve REST.

Network & secrets

Egress controls

Local networking off by default; hostname/subdomain and CIDR allowlists, exact/glob host patterns, runtime updates. Cloud supports explicit blocked/open/allowCidrs modes; SDK cloud default is open, so local isolation-by-default does not imply cloud egress blocked by default. No first-class deny-list documented.

Secrets

Local --secret-env/--secret-file inject readable plaintext; SSH-agent forwarding keeps key bytes on host but permits signatures. --credential and Smolfile network.credentials replace guest placeholders only on authorized HTTPS destinations so real secrets stay outside guest. No cloud-native secrets vault documented.

Bring your own cloud

Placement & use

Jurisdiction

United States: privacy policy says Google Cloud US regions and data processed in the United States. No exact hosted region codes disclosed. Self-host jurisdiction follows operator placement.

Advertised workloads

Untrusted/generated code, persistent coding-agent workspaces, warm branch fan-out, portable dev/CI environments, Linux services, headless browsers; local Vulkan desktop/computer-use and CUDA training/inference.

03 Capabilities 19 pass · 6 partial · 36 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 7/11

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not supported

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Supported

GPU computeGPU-backed instances available.

Supported

Multi-regionCompute placeable in more than one geographic region.

Not supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Partially supported

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 3/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Supported

Custom domainsBring-your-own domain via CNAME/DNS.

Not supported

Public preview URLsShareable per-deploy / per-branch URLs.

Supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not supported

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not supported

Email send / receiveSend and/or receive email from the workload.

Not supported

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not supported

Developer access 5/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Supported

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Partially supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not supported

AI & agents 3/12

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Not supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not supported

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Supported

Data 0/4

First-party databasePlatform-provided managed database.

Not supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not supported

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not supported

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not supported

Platform & operations 0/6

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not supported

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Partially supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not supported

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not supported

Organisation & security 1/9

Built-in authPlatform-provided authentication / IAM for workloads.

Not supported

SSO / SAMLEnterprise single sign-on.

Partially supported

Secrets managementFirst-class secrets storage / injection.

Partially supported

TeamsMulti-user team accounts.

Not supported

SharingShare a running workload/resource via link (optionally gated).

Partially supported

BYOCRuns inside the customer's own cloud account.

Not supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Portable self-contained VM artifact (.smolmachine)portable-vm-artifact
“Pack a machine, however you set it up, into a single `.smolmachine` file. Push it to any OCI registry, or run it as a self-contained executable that boots in under 200 ms with nothing to install.” github.com

04 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

10/11

10 full · 0 partial · 91% of applicable checks

llms.txt
Supported
“https://smolmachines.com/llms.txt: substantive docs/product/API/pricing/auth/skills index.”
llms-full.txt
Not supported
“https://smolmachines.com/llms-full.txt returns HTTP 404 HTML; robots points to llms.txt, not a comprehensive full dump.”
robots.txt AI policy
Supported
“robots.txt explicitly allows search engines and AI crawlers: User-agent: * / Allow: /.”
JSON-LD
Supported
“Homepage JSON-LD graph has Organization, SoftwareApplication, WebSite; software name/description and OSS/cloud Offer entries.”
Sitemap
Supported
“Fetchable substantive XML sitemap lists public docs/legal/pricing/registry pages; >5 URLs.”
Meta tags
Supported
“Homepage descriptive title, meta description, OG title/description/image and canonical URL.”
Markdown negotiation
Supported
“Homepage Accept:text/markdown serves clean product guide; docs Markdown twins and pricing.md are substantive.”
Content efficiency
Supported
“Homepage HTMLParser readable non-script/style UTF-8 text / raw HTML bytes = 9.14%, above 5% full-credit threshold.”
Docs discoverable
Supported
“Docs is a first-class homepage header link /docs reachable in raw HTML.”
Machine-readable pricing
Supported
“pricing.md has structured rates/plan tables; live unauthenticated /v1/pricing JSON corroborates amounts.”
No anti-bot wall
Supported
“Retained public landing/docs/legal/specs/rate card fetched without bot or consent challenge; ordinary optional 404s are not blocks.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

9/11

7 full · 2 partial · 82% of applicable checks

Public API
Supported
“https://smolmachines.com/docs/cloud/api-reference documents machine create/exec/files, authentication, lifecycle and quotas.”
OpenAPI spec
Supported
“Fetchable OpenAPI 3.1.0 at /openapi.json, 44 paths; generated schema can lag API and includes unsupported legacy volumes.”
MCP server
Not supported
“/.well-known/mcp HTTP 404; no first-party MCP server/endpoint or installable package in retained docs/llms guide.”
SDK packages
Supported
“Official smolmachines packages for Node/TypeScript, Python and Rust, linked in repository README.”
Auth documented
Supported
“auth.md documents bearer smk_ API keys, operation scopes, expiry, revocation and scoped minting.”
Self-serve credentials
Supported
“auth.md documents POST /v1/apikeys to mint narrower keys with existing authenticated key, no browser; initial root key still obtained through console sign-in. This documents issuance, not behavioral autonomous signup.”
Webhooks
Not supported
“No webhook delivery/signing docs; machine events/polling are not webhooks.”
CLI tool
Supported
“Official smolvm engine CLI plus smol cloud/local orchestration CLI.”
Error model
Supported
“Cloud API: RFC 9457 application/problem+json, stable code/detail/retryable, Retry-After and x-request-id; exec exit code model documented.”
Rate limits documented
Partially supported
“Per-tenant rate limiting and 429 with Retry-After documented, but concrete request ceilings and rate-limit remaining/reset headers not published.”
Agent config files
Partially supported
“Substantive /docs/guides/skills task-scoped script packets; /agents.md and /.well-known/agent HTTP 404, so one agent-config surface only.”

05 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 1

Codex CLI OpenAI
Supported
“codex … Coding-agent sandbox — Node.js, Python, git, ripgrep, and build-essential with the OpenAI Codex CLI (`codex`) pre-installed. Bring your own API key at runtime.”
Source smolmachines.com
Advertised via a prebuilt registry base machine (a ready-to-run .smolmachine), not a bespoke integration.

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

06 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 2

CCPA
self-attestedhostedSelf-attested; hosted service only.
“Depending on where you live (including… California under CCPA), you may have specific statutory rights to the same effect.”
Source smolmachines.comConfidence: medium
GDPR
self-attestedhostedSelf-attested in the privacy policy (rights honoured); no third-party report. Hosted service only — the OSS engine you run yourself is outside this scope.
“Depending on where you live (including the EEA/UK under GDPR …), you may have specific statutory rights… smol machines, inc. is the data controller.”
Source smolmachines.comConfidence: medium

Regions —

Regions are not disclosed on the public surface.

Country-level disclosure: Google Cloud US regions and data processed in United States. Exact hosted regions and placement choices not public; no multi-region availability inferred. Self-host placement is operator-defined.

Legal

Privacy notice Terms of service

07 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: Rust
Stars: 6,699
Forks: 326
Created: 18 Dec 2025
Archived: No

Activity

Last commit: 12 Oct 2026
Latest release: v1.27.1 · 12 Oct 2026
Issues open / closed: 31 / 246 · 89% closed

8 recent releases retained; latest v1.27.1, two releases published on 2026-10-12 and two on 2026-10-10.

Fetched via gh on 12 Oct 2026.

Self-hosting

Methods: binarysource-build
You operate: —

Apache-2.0 engine is free plus operator hardware/infra. Linux x86_64/aarch64 needs KVM; macOS needs Hypervisor.framework entitlements; native Windows x86_64 needs WHP. Standalone engine/CLI/serve API has no production fleet scheduler, placement, failover, tenant management, billing or managed durability. GPU is local/self-host only: Vulkan host stack or NVIDIA driver for CUDA remoting; GPU sharing is not hardware-partitioned multi-tenant isolation. Branch/checkpoint limits depend on host, runtime version and attached devices; Windows branches require --freeze-source.

Documentation signals 8/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

08 Company & presence Facts only, not scored

Company

Headquarters: unknown
Founded: unknown
Team size: unknown
Hiring: unknown

Activity

Last release: v1.27.1 (2026-10-12T06:38:07Z) github.com
Last blog post: Giving AI an undo button — September 24, 2026; next posts GPU remoting and Kubernetes dated July 14, 2026. smolmachines.com

Presence 5

Links found on the public surface scanned; not an exhaustive search.

09 Sources & method How this entry was produced

Public surface only

Everything here was read from smolmachines.com's unauthenticated pages, docs, pricing and repository on 12 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Sandbox products →