Sanity vs WeWeb
Side-by-side trajectory, velocity, and editorial themes.
Sanity is quietly wiring its CMS to be operated by agents as much as by humans.
Sanity is shipping on several fronts in parallel: a maturing MCP server and agent tooling, a Media Library growing real asset-management depth, and steady Studio and SDK ergonomics. The recent run is incremental but coherent — richer Media Library metadata and reference tracking, searchable reference fields, and a stream of MCP tool fixes. Nothing here reshapes the product; it is compounding polish on an already broad platform.
The clearest theme is agent-operability. The MCP server, a skills-install CLI command, agent-focused doc quickstarts, and copy-paste commands 'for humans and agents' all point at Sanity treating AI coding agents as a first-class way to drive the CMS. In parallel, Media Library is being built out toward a full DAM, and @sanity/presets is trimming schema boilerplate.
Expect the MCP and agent surface to keep expanding and Media Library to keep gaining DAM-grade features; the presets package suggests more ready-made schema building blocks ahead.
WeWeb is going AI-native, letting external tools build in your project
WeWeb is pushing its visual web builder toward AI-native development. It shipped MCP support so external AI tools can understand and build directly in a WeWeb project, then followed with in-app WeWeb AI gaining planning and task tracking plus MCP quality-of-life fixes. Underneath, the core keeps getting refined — a redesigned Supabase Select, formula columns in table views, and steady editor, navigation, and publishing polish.
The arc is toward a builder where AI is a first-class way to construct apps, whether through the in-app assistant or an external tool driving the project over MCP. Recent releases pair that agentic surface with data-layer depth (Supabase, formula columns) and deployment ergonomics, suggesting WeWeb wants AI-assisted building to sit on top of a solid, data-connected foundation rather than replace it. The messaging around 'AI, visual, or both' signals a deliberately hybrid workflow.
Expect WeWeb AI and MCP to keep maturing together — richer planning, more reliable agent edits — alongside continued Supabase and data-source depth, given how these two threads dominate the recent cadence.
See more alternatives to Sanity →
See more alternatives to WeWeb →