| What it does | On-device voice AI SDK with no cloud dependency
| Autonomous AI coding agent with deterministic program repair
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | CY
| ID
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Published models free for commercial use; custom models available as paid engagements.
| Core Basic: free (20 CLI / 15 Web runs per day, 50K daily AST tokens). Apex Pro: $11/month (100 CLI / 75 Web runs per day, 250K daily AST tokens). Sovereign Ultra: $44/month (400 CLI / 300 Web runs per day, 1.0M daily AST tokens). Annual subscriptions include 2 months free.
|
|---|
| 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
| - 4.1µs C-ABI latency native Rust Sub-Cortex execution
- Zero dirty diffs with strict AST grammar validation and dry-run verification
- Support for 6 production languages: Python, Rust, TypeScript/JavaScript, Go, C/C++, and Java
- Polyglot language engines with direct Tree-sitter CST surgery
- Machine-to-Machine sub-cortex infrastructure for autonomous agents
- Zero Code Retention policy with ephemeral in-memory processing
- 91.3% AST token pruning for repository context efficiency
- Multi-file repository context with automated test-runner verification
- Automated 5-Whys Root Cause Analysis and SRE incident diagnostics
- System-wide dependency mapping and security audit capabilities
|
|---|
| 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
| - Eliminates 95% of LLM token overhead through deterministic compiler verification instead of probabilistic inference loops
- Operates locally with strict Zero Code Retention policy—no code logging, storage, or model training usage
- Sub-microsecond repairs in CPU L1 cache without garbage collection pauses via native Rust FFI
- Engineered as M2M sub-cortex infrastructure for autonomous agents, not consumer chatbot utility
|
|---|
| 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 | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 0 |
|---|
| Citation Flow (Majestic) | 21 | 15 |
|---|
| Referring domains (Majestic) | 17 | 2 |
|---|
VoxRT
Kronumos