| What it does | A harness for comprehension: understand code better and faster, especially code AI agents write
| Fine-tuned small models for English-to-Bash command generation
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| Not given
|
|---|
| Pricing model | Paid
| Open source
|
|---|
| Pricing | $15 a month, free for a month from the first launch. One subscription covers all your Macs. Billed monthly through Polar; cancel anytime in the customer portal.
| Not given
|
|---|
| Key features | - User journey visualization for pull requests showing blast radius and impact
- AI-generated flow diagrams from code using Claude
- Drill-down to actual code and methods behind each step
- Call graph visualization showing method relationships
- AI question answering about code steps using Claude
- Offline analysis for most languages with .NET SDK support for C#
- GitHub integration for private repository access
- Persistent layout between runs for consistent navigation
| - 1.5B and 0.6B fine-tuned models
- 401,975 synthetic training examples
- 4-bit quantized models
- CLI with llama.cpp integration
- Command preview mode
- Covers file operations, text processing, Git, archives, networking
- Training data and checkpoints available
- Apache 2.0 and MIT licensed
- ALFA-updated benchmark evaluation
- Supervised fine-tuning with LoRA
|
|---|
| What makes it different | - Visualizes code as interactive maps with user journeys showing the full blast radius of changes
- Runs locally on your Mac with only Claude API calls going over the network
- AI-generated flow diagrams connect pull requests to actual business logic via real code methods
- Uses language-specific parsers for accurate code analysis instead of heuristics
- One subscription covers all your Macs with no signup or card required for first month
| - 70.7% pass rate on ALFA-updated benchmark vs 63.7% for competing models
- CPU-friendly quantized models
- Specialized for bash command generation from natural language
- Agentically trained with synthetic data generation and evaluation
|
|---|
| 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 | 36 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 6 |
|---|
| Citation Flow (Majestic) | 18 | 32 |
|---|
| Referring domains (Majestic) | 18 | 219 |
|---|
logPhase