| What it does | Code review for uncommitted git changes before you commit
| Codebase intelligence platform for AI agents and teams
|
|---|
| Stage | Startup
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | CA
| Not given
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | 5 free reviews with no signup or credit card, then $4.99 once for unlimited use on up to 2 Macs. A review includes every AI summary, explanation, and chat message for one repo for one day. No subscription; 30-day refund policy. Free 1.x updates included.
| Free: 2 public repos, 10 AI answers/month. Pro: $15/month (moving to $20/month in November, or $16/month yearly), includes private repos, auto-sync on every push, security scanning, $5/month AI credits. Teams: $20/seat/month with 3-seat minimum, includes 25 shared repos, shared $5/seat/month credit
|
|---|
| Key features | - Hunk-by-hunk code explanation with AI
- Interactive chat thread per hunk for follow-up questions
- Side-by-side before and after view of changes
- One-line AI summary for each file
- Saved chat threads and explanations that persist between sessions
- Support for OpenAI, OpenRouter, or any OpenAI-compatible endpoint
- API key stored securely in macOS Keychain
- Works with code written by humans or AI agents
- License works on up to 2 Macs
| - Code health scoring with defect prediction
- Blast radius and change impact detection
- Auto-generated documentation rebuilt on every commit
- Git intelligence: hotspots, owners and coupling detection
- Architecture and decision tracking
- MCP tools for Claude Code and Cursor
- PR bot with change review and test detection
- Security scanning: CVEs, secrets and reachability
- Dead code detection and unused exports
- Change Records with policy enforcement
|
|---|
| What makes it different | - One-time $4.99 purchase with no subscription or recurring fees
- Free trial with 5 reviews and no signup or credit card required
- Built specifically for reviewing uncommitted changes, not a general git client with chat attached
- Your code never leaves your chosen AI provider, never sent to DiffCue
- Interacts with AI agents from Cursor, Copilot, Claude Code, and Windsurf
| - Open source under AGPL-3.0, self-hostable with no LLM calls required to build the index
- Every published benchmark includes sample size, corpus and statistical methods
- Code health scores trained on years of real commits and defect fixes, with 0.74 AUC prediction accuracy
- Eliminates need to switch tools: integrates with Claude Code, Cursor, VS Code, GitHub and team dashboards
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 6 ▼ −1 (down) since last check | 10 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 8 |
|---|
| Citation Flow (Majestic) | 12 | 34 |
|---|
| Referring domains (Majestic) | 1 | 244 |
|---|
DiffCue
Repowise