| What it does | On-device voice AI SDK with no cloud dependency
| Memory, rules and git blame for your coding agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | CY
| DE
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Published models free for commercial use; custom models available as paid engagements.
| Free for personal use with all features; Team plan $20 per active seat per month, billed yearly (minimum 3 seats). First 10 teams pay $10 per active seat for 12 months.
|
|---|
| Key features | - Custom wake word detection with configurable threshold
- Streaming and batch automatic speech recognition
- Custom keyword spotting for voice commands
- Voice activity detection to identify speech
- Speech-to-intent with end-to-end processing
- Production binaries under 1 megabyte
- Models encrypted at rest with offline-first design
- NEON-accelerated battery-aware kernels
- Domain-specific model tuning
| - Session storage with secret redaction on local machine before upload
- Git blame integration showing which agent session wrote each code line
- Memory across agents allowing pickup of previous work
- Handoff between agents when Claude hits token limits
- Rules from corrections that persist across all agent sessions
- Session condensing showing only key moments and code
- Team rules reviewed like pull requests before reaching agents
- Team memory persisting when members leave
- Session attribution on pull requests showing which commits came from sessions
- MCP server for agents to search and learn from shared sessions
|
|---|
| What makes it different | - Runs entirely on device with no cloud round-trip or per-detection fees
- Published models free for commercial use with custom tuning available
- Lightweight runtime under 1 MB with predictable latency and battery efficiency
- Models designed and tuned specifically to your product domain
- Audio never leaves the device and models are encrypted at rest
| - Real sessions only, no fabricated runs, showing actual agent failures and interventions
- Secrets redacted on your machine before any data leaves, with server-side verification
- Open source MIT plugin with full control over your data
- Works with five different coding agents from one plugin
- Team data stays on your own PostgreSQL server if you choose
|
|---|
| 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) | Not checked yet ● no change since last check | 10 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 2 |
|---|
| Citation Flow (Majestic) | 21 | 35 |
|---|
| Referring domains (Majestic) | 17 | 10 |
|---|
VoxRT
KeepPlain