AI assistants and search decision
CNVS
A capable developer can build a useful cross-platform replacement in a few weeks using existing open-source assistant projects and LLM APIs; CNVS's durable advantages (native macOS binary, lifetime license, polished UX) are not structural moats shown on the site.
Visit website↗Built by Max Blade, who ships 3 products in this index
Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off64 h to build
$20/mo3 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All CNVS alternatives, with the arithmetic →
What a replacement has to do
- Orchestrate multiple LLM calls per canvas and display results
What it still won’t have
- Native macOS Swift application (CNVS advertises "Native macOS, built in Swift.")
- One-time founder pricing / lifetime license convenience (CNVS is sold as a one-time payment)
- Polished, shipped UX and buyer-provided agent templates and presets
- Marketing, community goodwill, and verified buyer trust signals shown on the site
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
CNVS does not publish a price we could read, so there is nothing to compare against. What building costs is below.
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 lightweight cross-platform desktop AI assistant (Electron or Tauri + React) that provides a canvas to create and run multiple agents in parallel. Stack: Electron/Tauri, React, Node.js backend, SQLite for local state, and usage of Web Speech API for voice input and OS TTS for audio output. Core features in scope: (1) canvas UI to create/delete named agents, (2) agent orchestration that sends/receives requests to configurable LLM APIs and shows streaming outputs, (3) voice command capture mapped to agent actions, (4) simple sandboxed runner to execute shell or Node scripts and capture stdout/stderr, (5) settings to store API keys locally and export/import canvases. Out of scope: native Swift macOS-specific optimizations, integrated commercial model licenses, App Store distribution packaging, and advanced IDE-like code intelligence. Include error handling for API failures and rate limits, unit tests for orchestration logic, and end-to-end tests for the UI flows.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 6 cited sources+3
- Evidence score60
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 · 6
Every page the run actually retrieved.
- official productCNVS — Command an army of agents with your voice
- official pricingCNVS pricing and offer
- official productPlatform detail
- official productParallel model orchestration
- open sourcearc53/DocsGPT
- open sourceszczyglis-dev/py-gpt
Integrity checks
What held up, and what did not.
