Skip to content
ProductArena

Rank #5 of 5 in E-commerce Platforms

Swell logo

Swell

Swell Inc. · commercial

swell.is ↗Try it →
PA Score17/100AGENT-READY30/100BUILT-IN AI5/100API5/100
MCP—CLI✓API✓
npm 2.2k/wk
ArenasE-commerce Platforms#5/5

Access

API docs ↗CLI docs ↗

Install

npmnpm install -g @swell/cli

Compare head-to-head

Shopify logovs ShopifyMedusa logovs MedusaWooCommerce logovs WooCommerceBigCommerce logovs BigCommerce

Alternatives to Swell →

Showcase

Swell homepage screenshot
homepage · captured Sep 2026 · view live ↗
Swell docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with Swell before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$mktemp -d && npm install @swell/cli && swell --versionrecorded session — replayed, not live
recorded 2026-09-08 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

19.3/100

Ai commerce — stories about ai commerce in this arenaAi commerceevidence →

Stories about ai commerce in this arena

0.0/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

17.3/100

B2b wholesale — stories about b2b wholesale in this arenaB2b wholesaleevidence →

Stories about b2b wholesale in this arena

30.0/100

Catalog inventory — stories about catalog inventory in this arenaCatalog inventoryevidence →

Stories about catalog inventory in this arena

57.4/100

Checkout conversion — stories about checkout conversion in this arenaCheckout conversionevidence →

Stories about checkout conversion in this arena

20.0/100

Extensibility apps — stories about extensibility apps in this arenaExtensibility appsevidence →

Stories about extensibility apps in this arena

43.4/100

Headless apis — stories about headless apis in this arenaHeadless apisevidence →

Stories about headless apis in this arena

75.0/100

Multi channel — stories about multi channel in this arenaMulti channelevidence →

Stories about multi channel in this arena

10.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

19.7/100

Payments — stories about payments in this arenaPaymentsevidence →

Stories about payments in this arena

12.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Storefront experience — stories about storefront experience in this arenaStorefront experienceevidence →

Stories about storefront experience in this arena

29.0/100

Taxes shipping — stories about taxes shipping in this arenaTaxes shippingevidence →

Stories about taxes shipping in this arena

0.0/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full7/10T

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3noneuntestednone yet

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10C

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1partial6/10C

Model products with variants, options, and custom fields/metafields that fit my catalog, not a fixed template C

Catalog

merchantCatalog inventory — stories about catalog inventory in this arenaCatalog inventory3full9/10C

Build a fully custom headless storefront on a documented storefront API or first-party frontend framework C

Headless

developerHeadless apis — stories about headless apis in this arenaHeadless apis3full8/10T

Manage the full commerce lifecycle programmatically — create products, edit orders, issue refunds, trigger fulfillments — through the admin API C

Admin api

developerHeadless apis — stories about headless apis in this arenaHeadless apis3full7/10T

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial5/10C

Launch a polished storefront from professionally designed themes and customize layout, sections, and branding without code C

Themes

merchantStorefront experience — stories about storefront experience in this arenaStorefront experience3partial5/10C

Customize checkout — fields, branding, discounts, and validation logic — through supported extension points rather than forking checkout C

Checkout

developerCheckout conversion — stories about checkout conversion in this arenaCheckout conversion3partial4/10C

Extend my store from a marketplace of vetted apps and extensions covering the long tail of features C

Apps

merchantExtensibility apps — stories about extensibility apps in this arenaExtensibility apps3partial4/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial3/10C

A shopping agent can discover my store's products and build carts through a documented agent-commerce endpoint on the store (MCP/UCP), not by scraping C

Agentic checkout

ai-native userAi commerce — stories about ai commerce in this arenaAi commerce3none0/10

Take payments with the platform's integrated processing — published card rates, payouts, and fraud tooling — without wiring a third-party gateway C

Processing

merchantPayments — stories about payments in this arenaPayments3none0/10

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3n/auntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3n/auntestednone yet

Inject custom backend logic — discounts, shipping rules, validation — as serverless functions or hooks that run inside the platform C

Functions

developerExtensibility apps — stories about extensibility apps in this arenaExtensibility apps2full8/10C

Customize storefront code with a documented templating layer, local preview, and version-controlled theme deploys C

Theme dev

developerStorefront experience — stories about storefront experience in this arenaStorefront experience2partial7/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial7/10T

Build custom apps and extensions with official SDKs, scaffolding tooling, and a documented review/distribution path G

App dev

developerExtensibility apps — stories about extensibility apps in this arenaExtensibility apps2partial6/10T

Bulk import, export, and edit the catalog — CSV or API — without touching products one at a time C

Catalog ops

operations leadCatalog inventory — stories about catalog inventory in this arenaCatalog inventory2partial6/10C

Choose among third-party payment gateways and charge in multiple currencies when the built-in option doesn't fit C

Processing

merchantPayments — stories about payments in this arenaPayments2partial5/10C

Inventory tracks across multiple locations with stock adjustments and fulfillment from the right warehouse C

Inventory

operations leadCatalog inventory — stories about catalog inventory in this arenaCatalog inventory2partial5/10C

Sell B2B and wholesale — customer-specific price lists, volume pricing, quotes or net-terms invoicing — alongside DTC G

B2b

merchantB2b wholesale — stories about b2b wholesale in this arenaB2b wholesale2partial5/10C

Sell internationally with localized storefronts, multi-currency pricing, translations, and duties handled G

Global

merchantMulti channel — stories about multi channel in this arenaMulti channel2partial5/10C

Buyers can pay with accelerated wallets — Apple Pay, Google Pay, PayPal, platform one-click — without re-entering details C

Checkout

merchantCheckout conversion — stories about checkout conversion in this arenaCheckout conversion2partial4/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial4/10C

An agent can take an order through its post-purchase lifecycle — status, fulfillment, returns — via documented APIs and webhooks without a human in the admin C

Agent ops

ai-native userAi commerce — stories about ai commerce in this arenaAi commerce2none0/10

List and sync products to external channels — marketplaces, social commerce, shopping feeds — from one catalog C

Channels

merchantMulti channel — stories about multi channel in this arenaMulti channel2none0/10

My products are discoverable by AI agents and answer engines through a cross-merchant catalog or feed built for agents C

Agent discovery

ai-native userAi commerce — stories about ai commerce in this arenaAi commerce2none0/10

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2none0/10

Checkout shows live carrier rates and I can buy labels and track shipments from the platform C

Shipping

operations leadTaxes shipping — stories about taxes shipping in this arenaTaxes shipping2noneuntestednone yet

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Sales tax and VAT are calculated automatically per jurisdiction, with rates kept current and reports I can file from C

Taxes

merchantTaxes shipping — stories about taxes shipping in this arenaTaxes shipping2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

Sell in person with a point-of-sale that shares the same catalog, inventory, and customers as my online store C

Pos

merchantMulti channel — stories about multi channel in this arenaMulti channel2noneuntestednone yet

Abandoned carts and checkouts trigger recovery emails or links so I can win the sale back C

Conversion

merchantCheckout conversion — stories about checkout conversion in this arenaCheckout conversion1noneuntestednone yet

Manage content — pages, blogs, media — alongside my products from the same admin C

Content

merchantStorefront experience — stories about storefront experience in this arenaStorefront experience1noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 45 stories with headroom

What would move Swell’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product

    nonemoves Built-in AIimpact 45

    Swell's docs describe making the platform friendly to external AI coding agents (schema discovery endpoint, file-based model generation, CLI hooks) but there is no evidence of a built-in AI assistant embedded in the Swell dashboard/product that a user can delegate tasks to directly.

  2. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    Swell is an e-commerce platform; evidence describes CLI, functions, webhooks, and an AI-assisted schema/model workflow, but nothing indicates Swell can consume external MCP servers or plug in third-party tool sets.

  3. Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server

    nonemoves agent-readyimpact 45

    Evidence shows a CLI, webhooks, and 'agent'-friendly file-based contract, but no mention of an official MCP server or MCP protocol support anywhere in the docs or probes; probes even show llms.txt and openapi.json as 404, suggesting no structured agent-integration endpoint.

  4. Ai commerce — stories about ai commerce in this arenaA shopping agent can discover my store's products and build carts through a documented agent-commerce endpoint on the store (MCP/UCP), not by scraping

    nonemoves PA Scoreimpact 30

    The evidence shows Swell's AI features target developers building on Swell (schema-introspection API for building resources, CLI tooling) rather than a documented agent-commerce endpoint (MCP/UCP) for external shopping agents to discover products or build carts.

  5. Payments — stories about payments in this arenaTake payments with the platform's integrated processing — published card rates, payouts, and fraud tooling — without wiring a third-party gateway

    nonemoves PA Scoreimpact 30

    Evidence shows Swell relies on third-party gateways (PayPal, Braintree) for payment processing rather than offering its own integrated processing with published card rates, payouts, or fraud tooling.

  6. Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs

    nonemoves agent-readyimpact 30

    A direct probe of the documented llms.txt path returns 404, and no evidence pack item shows a dedicated agent-oriented docs endpoint (e.g., markdown docs, llms.txt, or similar) that an agent could be pointed at; the swell.is/ai marketing page describes AI-friendly schema/API concepts but not a llms.txt or agent-consumable doc file.

  7. Agenticness — how well agents can access and operate the productGet AI-generated insights and suggestions from my data inside the product

    nonemoves Built-in AIimpact 30

    Swell's AI-related docs focus on making its schema/API machine-readable for external agents to build integrations (schema discovery, model generation, CLI loop), not on the product itself surfacing AI-generated insights or suggestions from store data to users.

  8. Agenticness — how well agents can access and operate the productOperate the product with natural-language commands

    nonemoves Built-in AIimpact 30

    Missing: any chat/NL command interface, conversational operation of dashboard or storefront, or documentation of natural-language input being parsed/executed by the product.

Showing the top 8 of 45 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map10 surfaces · 26 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

Apps docs16 stories

Backend API docs9 stories

For developers docs9 stories

Features docs8 stories

AI docs7 stories

OpenAPI spec6 stories

llms.txt3 stories

Headless commerce docs3 stories

Changelog docs2 stories

Pricing docs1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$mktemp -d && npm install @swell/cli && swell --versionreproduced
$ mktemp -d && npm install @swell/cli && swell --version
\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-
added 327 packages in 5s
-@swell/cli/2.9.16 darwin-arm64 node-v26.0.0
proves: Use an official CLIrecorded 2026-09-08
$curl -s https://raw.githubusercontent.com/swellstores/skills/main/README.md | head -8reproduced
$ curl -s https://raw.githubusercontent.com/swellstores/skills/main/README.md | head -8
# Swell Skills

Your AI coding agent, now fluent in [Swell Commerce](https://www.swell.is) development.

Install once and your agent picks up everything it needs to build, validate, and ship a [Swell App](https://developers.swell.is/apps): the file system contract, the `swell` CLI, the validate → deploy → verify cycle, and the non-obvious rules for payment, shipping, and tax integrations.

Swell Apps package data models, admin content views, settings, notifications, webhooks, edge functions, and integration extensions into a single store extension.
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-08

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 19 testable claims verified · 2 contradicted → integrity 5/100

39 distinct capability claims found in Swell’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

12

Unverified

2

Contradicted

9

Undersold

Verified (8)
Unverified (19)
Contradicted (2)
Undersold (9)
Claims outside our story set (10)

Real capability claims found in Swell’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Merchants can design category trees via drag-and-drop for product discovery”

    source ↗

  • “Team members can be assigned specific roles and permissions”

    source ↗

  • “Products can be sold via one-time purchase, subscription plans, or try-before-you-buy”

    source ↗

  • “Purchase links let merchants pre-configure a cart and send customers to a dedicated checkout URL”

    source ↗

  • “A single product can support multiple purchase options simultaneously”

    source ↗

  • “Product bundles can be created to increase revenue”

    source ↗

  • “Detailed performance reports are available for tracking store analytics”

    source ↗

  • “Cross-sells and upsells can be shown on product pages and at checkout”

    source ↗

  • “SMS-only opt-in is supported for Klaviyo subscription integration”

    source ↗

  • “Physical and digital subscriptions are supported in one system”

    source ↗
Suggest a story for these →

Business model

subscription-flatusage-basedenterprise-custom

Revenue-ceiling plans billed yearly: Starter $29/month (to $50K annual sales), Basic $79, Standard $299, Unlimited $2,250 (to $5M) — overages like $5 per extra 100K API requests; free trial, enterprise custom.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score22 (Sep 8 '26)17 (Sep 16 '26)
Agent-ready43 (Sep 8 '26)30 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)