| What it does | Fine-tuned small models for English-to-Bash command generation
| Persistent memory for AI coding agents that persists across sessions and tools
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Open source
| Free trial
|
|---|
| Pricing | Not given
| Early access, enabled per company while onboarding founding teams. 50 free credits on signup, no credit card required.
|
|---|
| 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
| - Preferences injected into every session on every AI coding tool
- Three scopes: personal, project, and company
- Auditable receipt for every memory injection
- Owner-editable and hard-deletable memories on demand
- Import from existing ChatGPT or Claude exports
- Engineering and general modes for non-engineering teams
- Works with Claude Code, Cursor, Codex and Grok Build
- Private stays private, every serve leaves a receipt
- Memories filtered per scope, not hidden in UI
- No credit card required to start
|
|---|
| 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
| - Solves the hidden tax of repeating the same instructions to AI agents every session
- Keeps personal preferences private while maintaining team and company policies
- Reduces context window token usage by 2.7x compared to raw history
- Immediate deletion with bodyless receipts for audit compliance
- Attached to you, not to a vendor's session store
|
|---|
| 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 | 3 ● no change since last check |
| Trust Flow (Majestic) | 6 | 4 |
| Citation Flow (Majestic) | 32 | 22 |
| Referring domains (Majestic) | 219 | 40 |