| What it does | Fine-tuned small models for English-to-Bash command generation
| An agentic engineering platform that takes assigned issues to reviewed, tested pull requests
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| NL
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Not given
| Free: 3 credits when you connect your first repository. Credit packs: 10 credits for $49, 50 credits for $199, 100 credits for $349 (one-time purchases, credits never expire). Starter plan: $170/month for 50 credits plus 5 agents at once. Scale plan: $480/month for 160 credits plus 8 agents at once.
|
|---|
| Key features | - 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
| - Planner agent creates implementation and testing specs from tickets and docs
- Builder agent writes code, runs formatters, linters, type checks and tests in sandbox
- Reviewer agent validates code against plan and project guidelines
- Tester agent runs deployment pipeline and validates acceptance criteria
- Real-time mission monitoring with cost attribution per stage
- Configure different agents and models per role
- Integrates with Linear, Jira, GitHub Issues or CLI
- Human checkpoints to pause pipeline at any stage
- Zero-trust security with encrypted credentials never entering sandbox
- Scheduled maintenance tasks with auto-merge option
|
|---|
| What makes it different | - 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
| - Only platform where all agents review and test before person reads PR
- Mix agents and models by role for cost and quality optimization
- Bring your own AI provider contracts and run inference on your accounts
- Works with existing tools, repositories and CI/CD pipelines
|
|---|
| 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) | 36 ● no change since last check | 6 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 6 | 1 |
|---|
| Citation Flow (Majestic) | 32 | 29 |
|---|
| Referring domains (Majestic) | 219 | 53 |
|---|
SHIP