Spanlens VS ViewForge

Spanlens's answer

I was building LLM apps on the side and kept pasting token counts into a spreadsheet to figure out what each feature cost me. The tools I tried were either acquired mid-migration, closed source, or heavier to self-host than the app I was trying to monitor. So in April 2026 I started building the tool I actually wanted: change one line, see every request. It launched in June 2026, and the whole codebase went up on GitHub under MIT from day one.

ViewForge's answer:

ViewForge came out of agency work. Normal View was building for a parts retailer running roughly 12,000 SKUs who needed fitment search, and every app we evaluated stored the merchant's compatibility data in the vendor's own database.

That is a strange trade when you look at it directly. Fitment data is genuinely expensive to produce — it is weeks of work — and the merchant would not own the result. It would belong to whichever app happened to be installed that year.

Shopify metaobjects made a different answer possible: write fitment as native structured data inside the merchant's own store. The theme reads it, the Storefront API queries it, Admin GraphQL exports it, and it is still there after an uninstall. That decision is what the rest of the app is built around.

Everything else came from real catalogs rather than a roadmap. Eight verticals exist because a tractor catalog is not Year/Make/Model. Smart Parse exists because that retailer had already written fitment into 12,000 product titles, and nobody was ever going to retype them.

Spanlens's answer

The entire product is MIT licensed, including the dashboard, evals, and prompt A/B testing. There is no separate enterprise edition. Everything ships in one repo you can run with a single Docker Compose file. Integration is one line: you change the baseURL on your OpenAI, Anthropic, or Gemini client, and every call gets logged with its full body, token counts, cost, and latency. A few things that are usually paid add-ons come built in, like agent traces with a critical path view, A/B tests that use Welch's t-test to tell you whether a difference is real, and a recommender that flags cheaper models based on the traffic you actually send.

ViewForge's answer:

Three things. (1) Data ownership: ViewForge writes fitment as Shopify metaobjects native to your store — most competitors store fitment in their own database. (2) 8 verticals out of the box: auto, motorcycle, tractor, marine, power equipment, bicycle, printer, electronics — most competitors are automotive-only. (3) Smart Parse: extract fitment automatically from your existing product titles and descriptions instead of re-typing everything.

Spanlens's answer

Mostly because of where the market went. Helicone was acquired, LangSmith is closed source, and self-hosting Langfuse takes real setup work. Spanlens fills the gap those tools left: setup in about five minutes, one Docker Compose file if you want the data on your own servers, and no feature gating between free and paid tiers. To be fair, if you need SOC 2 reports and enterprise support today, the bigger platforms are ahead. If you want request logs, costs, and traces without adopting a heavy platform, that is what Spanlens was built for.

ViewForge's answer:

Data ownership. Fitment lives in your Shopify metaobjects, so uninstalling does not take your compatibility data with it. Convermax, EasySearch and PartFinder all keep it in their own databases, and getting it back depends on their export tooling on the day you cancel.

Cost at the low end. The search widget, the compatibility table on the product page and the saved-vehicle garage are all on the free tier, up to 50 products, with no expiry. EasySearch puts the table and the garage behind its $75/month Premium plan. Convermax starts at $250/month.

Automotive and non-automotive coverage. Eight built-in templates, and fully custom templates from $19/month, for catalogs that do not decompose into Year/Make/Model at all.

Spanlens's answer

Developers who ship LLM features in production apps. The typical user is a solo developer or a small team that added OpenAI or Anthropic calls to their product and now has no clear picture of what those calls cost or why some are slow. Agent builders are the second group, since multi-step workflows are hard to debug without traces. It is a developer tool through and through: if you don't touch code, you won't get much out of it.

ViewForge's answer:

Shopify merchants whose customers need to know whether a part fits before they will buy it — and who do not have an engineer on staff to build that themselves.

Concretely: auto and truck parts retailers, powersports and motorcycle dealers, tractor and agricultural parts sellers, marine and outboard suppliers, small-engine and power equipment stores, bicycle and e-bike component shops, printer supply merchants, and electronics accessory sellers.

Catalog sizes run from a few dozen products on the free tier up into the tens of thousands; it is running in production on a catalog of roughly 40,000 SKUs. The common thread is not the industry — it is that "does this fit my thing" is the question deciding the sale.

Spanlens's answer

We don't publish customer names yet. Spanlens launched in June 2026, and most users so far are indie developers and small AI teams.

Spanlens's answer

TypeScript across the stack. The dashboard is Next.js, the API and proxy run on Hono, and data is split between Supabase Postgres for accounts and relational data and ClickHouse for request logs, which grow fast. The repo is a pnpm monorepo that also holds the JavaScript and Python SDKs, a CLI, and an MCP server. Self-hosting runs on Docker Compose, and OpenTelemetry traces can be ingested over OTLP.

ViewForge's answer:

• TypeScript
• Shopify metaobjects, as the fitment data store
• Shopify theme app extensions for the storefront components: fitment search, saved-vehicle garage, compatibility table, product-page fit notice
• Shopify Storefront API, for querying fitment from the theme
• Shopify Admin GraphQL API, for writing and exporting fitment records
• NHTSA vehicle database, for VIN decoding
• ACES and PIES XML parsing, for automotive catalog import