Local-first desktop software

Know whether the software you’re building matches what you intended.

Building with AI moves fast. CodeCaddie connects your product goals to evidence in a committed repository snapshot, highlights the gaps, and helps you decide what to ask your coding agent to fix next.

A complete loop

Give your coding agent a better next task.

Synthetic teaching example: customers should find relevant documents by searching their content. The walkthrough below uses the project’s small demo fixture; it is not a saved analysis, customer result, or benchmark.

  1. Set the goal

    “Customers can find relevant documents by searching their content.” Check that results respond to the query, rank by relevance, and are empty when nothing matches.

  2. Review the gap

    The synthetic fixture’s search returns a fixed result, and its test checks only one query’s result count. These are fixture facts; a real report must validate its own evidence at the analyzed commit.

  3. Give the agent a focused task

    “Implement query-dependent document search and ranking. Add tests for relevant, irrelevant, and unmatched queries. Review the report’s evidence before editing, and report the tests you ran.”

  4. Commit and recheck

    Review the patch, run the tests, and commit it. Analyze again against the same goal and inspect the new evidence. A score change alone does not establish improved customer outcomes.

Walk through the complete example

CodeCaddie offers three action paths: fix the implementation, revise the goal contract, or audit the analysis.
Action choices for the synthetic Document Search project in a macOS development build. Choose what needs to change before creating a prompt for your coding agent.

Grounded goals

Start with the product, not a generic checklist.

Add notes or explicitly selected PDF, PowerPoint, Word, text, or Markdown materials. CodeCaddie extracts bounded text only for the generation run, grounds product facts in page, slide, or paragraph identifiers, and proposes six to nine editable goals.

  • At least two durable business and product outcomes.
  • Required observability, testing, security, recovery, and safe-release goals.
  • Conditional platform goals such as tenant isolation, integration contracts, AI controls, and scale safeguards only when the product context supports them.

Visible provider activity

See what the analysis is doing.

The activity stream names the current phase and, when practical, the repository-relative file and pass counter. It never includes the device’s absolute path, search text, repository source, prompts, or attached-document text.

Invalid or incomplete provider output fails visibly. CodeCaddie preserves the approved goals instead of disguising a provider failure with generic fallback content.

Evidence-backed report

Turn repository evidence into a decision.

Every saved analysis is pinned to the exact scanned commit. CodeCaddie separates supported checks, demonstrated gaps, missing evidence, and checks it could not verify. Weighted support measures support among assessed checks, weighted by goal priority; unverified checks are excluded and shown separately. It is not test coverage or a percentage of finished features. Reports retain validated evidence coordinates instead of source excerpts.

CodeCaddie recommendations with verified references and a warning that some goal criteria were omitted or failed validation.
A real analysis of the synthetic Document Search project in a macOS development build. Recommendations retain verified references, and the report warns that some goal criteria were omitted or failed validation.

The trust boundary

CodeCaddie keeps source out of its stored state.

CodeCaddie never accepts provider credentials and never puts repository source in its storage, reports, IPC, logs, recovery exports, or provider diagnostics. An already-installed Codex, Claude, or Grok provider may process a disposable single-commit snapshot under that provider’s authorization, settings, privacy terms, and organizational policy.

Immutable evidence

Every architectural claim points to the scanned commit, repository-relative path, line range, and content hash.

Bounded analysis

The original checkout is untouched. Tools receive a bounded, history-free snapshot with inert symlinks.

Ephemeral product context

Selected document contents go to the chosen provider only during goal generation. CodeCaddie stores the local reference and hash, never the extracted text.

Native desktop app

Explore the project. Build your first report.

Download CodeCaddie for macOS and turn your repository into an evidence-backed report. Stable releases come from GitHub. The app verifies release identity and integrity before asking to install an update.

macOS

Universal Mac app

One universal ZIP containing the signed and notarized app for Apple Silicon and Intel Macs running macOS 13 or newer.

Download for macOS
Windows

Windows app

The Windows installer is not available yet.

Coming soon

CodeCaddie has no account. Live analysis requires an installed, authorized Claude, Codex, or Grok CLI; provider charges and policies may apply. Build the developer edition.