AI assistants and search decision
Respira for WordPress
A capable developer can build a narrow replacement (Gutenberg-only safe-edit pipeline + MCP proxy) in a few weeks, but reproducing Respira's multi-builder tool catalog, WooCommerce add-on, persistent memory, and polish is not realistic without significant additional engineering.
Visit website↗$9/mo
$108/yr
Read off the official pricing page.
$100one-off53 h to build
$20/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 4 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Agent -> MCP server -> WordPress plugin duplicates target content -> agent edits duplicate via tool endpoints -> admin reviews and approves -> plugin applies change
What it still won’t have
- Support for 16+ page builders and the 300+ MCP tool catalog
- WooCommerce add-on with 105 commerce tools and store-specific toolset
- Resonance persistent site memory and enforced rules
- Polished cross-builder SafeEdit, TimeSnap snapshots, and built-in audit telemetry
- Integrations with Claude Cowork, Cursor, and other agents out of the box
What remains hard
- Execution quality
The leading AI infrastructure layer for WordPress.
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal Respira-like system that enables safe AI edits for a single WordPress site (Gutenberg only). Stack: WordPress plugin (PHP, WP REST API) + MCP proxy server (Node.js, Express). Core features in scope: (1) plugin endpoints to list pages, create a duplicate of a page/post, accept edited content and mark as proposed, (2) admin wp-admin interface to view diffs of proposed edits, approve/rollback, and an activity log, (3) MCP server that authenticates an agent via an API key, forwards a small subset of MCP tool calls (list_pages, read_page, create_page_duplicate, update_page), and signs events, (4) serialize/deserialize Gutenberg blocks for safe edit roundtrip, (5) a CLI install script to register an API key and test connection. Out of scope: multi-builder support (Elementor, Divi, etc.), WooCommerce store tools, persistent site memory (Resonance), multi-tenant/site dashboards, advanced telemetry. Require: authentication, input validation, error handling, basic unit and integration tests, and docs for setup and connecting one agent.
How we checked
How the score was reached
- Partly verdict base52
- 3 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score62
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productRespira for WordPress
- official pricingPricing — WordPress AI Infrastructure | Respira
- official docsIntroduction to Respira for WordPress - Documentation
Integrity checks
What held up, and what did not.
