A Friendly, local AI assistant by Amphydia
¡BERT CLI is now officially out of Beta phase!
Visit berts Official GitHub Page here: Bert CLI official Page
This is Software Licensed Under Apache 2.0.
- For licensing terms, see LICENSE.
Bert is designed as a reliable AI assistant, something you can always rely on, you can see Bert as a Friend, as a service, as a companion, or as something else that you could value.
# Directly from PyPI Package:
pip install bert-cli
bertGo to Bert CLI official Page.
Claim yout token -
Then run bert and use:
/*token YOUR-TOKEN-HERE
- ✅ ESC Interrupt — Stop generation mid-stream
- ✅ Token-by-token Streaming — See responses appear naturally
- ✅ Thinking Display — See model's reasoning with
/*think - ✅ Path-aware File Inspection — Use
@path/to/filein queries - ✅ Automatic Context Compression — Never lose context
- ✅ Weekly Token System — 20K tokens free per week
- ✅ Gradient UI — Beautiful color-coded model names
For more info visit: Bert CLI official Page
| Model | Base | VRAM | Features |
|---|---|---|---|
| Bert Nano | LiquidAI/LFM2-700M | ~2GB | Ultra-fast |
| Bert Mini | LiquidAI/LFM2-1.2B | ~4GB | Balanced |
| Bert Main | Qwen/Qwen3-1.7B | ~5GB | Thinking 🧠 |
| Bert Max | LiquidAI/LFM2-2.6B | ~8GB | Reasoning |
| Bert Coder | Qwen/Qwen2.5-Coder-1.5B-Instruct | ~4GB | Code |
| Bert Max-Coder | Qwen/Qwen2.5-Coder-3B-Instruct | ~8GB | Heavy Code |
bert --ver # Show version
bert --info # Show info
bert --del # Remove Bert data (~/.bert)
bert --help # Show helpSwitch Models:
bert nano # Fastest (0.7B)
bert mini # Balanced (1.2B)
bert main # Flagship (1.7B)
bert max # Most capable (2.6B)
bert coder # Code-optimized (1.5B)
bert maxcoder # The best for Code (3B)
Change Quantization:
bert int4 # Balanced ⭐
bert int8 # High quality
bert fp16 # Best quality (all platforms)
bert fp32 # Full precision / CPU
Other Commands:
/*help # Show all commands
/*status # Show current status
/*clear # Clear screen
/*exit # Exit Bert
| Component | Minimum | Recommended |
|---|---|---|
| RAM | 8GB | 16GB+ |
| VRAM | 3GB | 6GB+ |
| Python | 3.8 | 3.10+ |
| Storage | 30GB | 40GB |
| Platform | INT4/INT8 | FP16 | FP32 |
|---|---|---|---|
| Linux | ✅ | ✅ | ✅ |
| Windows | ✅* | ✅ | ✅ |
| macOS | ❌ | ✅ | ✅ |
Remove Bert data:
bert --del-
GitHub Issues: github.com/Amphydia/bert-cli/issues
-
Email: mnisperuza1102@gmail.com
When reporting issues, include:
- Bert version (
bert --ver) - Your OS (Windows/Linux/macOS)
- Error message
Thanks for Using Bert CLI ❤️
Reliable as always.
Amphydia — 2025
