| What it does | The coding agent that runs on your machine
| Point at anything on your Mac and speak to give your coding agent a brief with screenshots
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| IN
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| Pricing | Developer: $19.99/month or $199.99/year with 30-day free trial. Business: $99.99/month per seat or $995/year with 30-day free trial. Enterprise: Custom pricing.
| Free: two hours of monthly transcription included. Pro (monthly): $6.99/month for ten hours of transcription. Pro (yearly): $69/year for ten hours of transcription. Pro (lifetime): $169 one-time for ten hours of transcription.
|
|---|
| Key features | - Bring your own API key for Claude, GPT, Gemini
- Plan-gate and write-gate safety controls
- Universal AST refactoring across 21 languages
- Persistent project memory and skill files
- Full MCP (Model Context Protocol) client
- Terminal CLI with same agent and memory
- Local OpenAI-compatible API endpoint
- Local JSONL audit log for compliance
| - Point and speak to create briefs with annotated screenshots
- Works with Claude Code, Cursor, Codex, Windsurf, ChatGPT, Claude.ai and more
- Mixed-language support in single sentence
- Three customizable persona templates for brief format
- Offline operation with fallback to on-device processing
- Automatic credential detection and withholding
- One-line command installation
- No account or sign-up required
|
|---|
| What makes it different | - Runs fully offline with no per-token costs, unlike cloud coding tools that bill by the token
- Safety-first with plan-gate and write-gate controls before any file is changed
- Model-agnostic: same editor and safety controls whether using local or cloud models
- Works entirely on your machine with no code leaving your device in local mode
- Whole-codebase semantic awareness for accurate edits across multiple files
| - Everything stays on your Mac—no data is kept on servers, and screenshots never leave unless you send them to an agent yourself
- Automatic task memory means your agent remembers context from previous conversations about the same issue
- Fully open source under MIT licence so you can verify all privacy and security claims
- Supports mixed-language voice input in a single sentence
|
|---|
| 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) | 18 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 3 |
|---|
| Citation Flow (Majestic) | 26 | 25 |
|---|
| Referring domains (Majestic) | 54 | 38 |
|---|
GIDE
Deiko