update readme

README.md

@@ -3,7 +3,7 @@
 
 regspy is a regex pattern generator, you enter some data -> select what you want matched and or not matched -> ??? -> Pattern!
 
-![alt text](https://d1pz4mbco29rws.cloudfront.net/public/regspy.gif)
+![regspy demo](https://d1pz4mbco29rws.cloudfront.net/public/regspy.gif)
 
 This project started as me trying to learn dspy, its vibe coded to shit and back but it works and has some accomplishments:
  - Runs on small models with 3B parameter at a minimum, so it should run on anything.
@@ -36,7 +36,7 @@ But if you're a everyday smooth brain like me that needs a simple pattern on the
 - **AutoHotkey v2.0** - [Download](https://www.autohotkey.com/)
 - **Python Libs**:
   ```bash
-  pip install dspy grex ollama
+  pip install dspy grex ollama modaic
   ```
 - **Ollama**:
   ```bash
@@ -48,27 +48,6 @@ But if you're a everyday smooth brain like me that needs a simple pattern on the
   AutoHotkey64.exe regspy.ahk # Or just double click regspy.ahk
   ```
 
-### CLI flags
-
-```bash
-# Run test suite
-python regexgen.py --test
-
-# Pre-compile for faster runtime
-python regexgen.py --compile
-
-# Generate regex from JSON input
-python regexgen.py input.json output.json
-
-# With custom config
-python regexgen.py input.json output.json --config config.json
-
-# Dataset management
-python regexgen.py --list-dataset output.json
-python regexgen.py --add-example example.json
-python regexgen.py --delete-example <index>
-```
-
 ## Architecture
 
 ```
@@ -90,4 +69,72 @@ The Config tab allows session-level adjustments:
 - **Max Attempts**: Refinement iterations (default: 10)
 - **Reward Threshold**: Stop early if score exceeds (default: 0.85)
 - **Scoring Weights**: Adjust the 5 criteria weights
-- **Context Window** (`num_ctx`): Ollama context size (default: 8192). Ollama defaults to 4096 which can truncate prompts with many training examples. If you see "truncating input prompt" warnings in Ollama logs, bump this up. Uses ~200MB extra VRAM per 4K increase on 3B models.
+- **Context Window** (`num_ctx`): Ollama context size (default: 8192). Ollama defaults to 4096 which can truncate prompts with many training examples. If you see "truncating input prompt" warnings in Ollama logs, bump this up. Uses ~200MB extra VRAM per 4K increase on 3B models.
+
+## Modaic Hub
+
+RegSpy uses Modaic's `PrecompiledProgram` so you can publish and load programs with bundled prompts, config, and optionally code.
+
+### Push to Modaic Hub
+
+Use the helper script:
+
+```bash
+uv run push.py your-username/regspy --with-code
+```
+
+Or directly in Python:
+
+```python
+from regspy import RegexConfig, RegexProgram
+
+program = RegexProgram(RegexConfig())
+program.push_to_hub("me/regspy", with_code=True)
+```
+
+### DSPy Programs: Auto Classes
+
+Load a program:
+
+```python
+from modaic import AutoProgram
+
+program = AutoProgram.from_precompiled("raet/regspy")
+```
+
+Load a config:
+
+```python
+from modaic import AutoConfig
+
+config = AutoConfig.from_precompiled("raet/regspy")
+```
+
+Override a config:
+
+```python
+from modaic import AutoProgram
+
+program = AutoProgram.from_precompiled(
+    "raet/regspy",
+    config={"use_cot": False, "temperature": 0.2},
+)
+```
+
+Specify runtime parameters:
+
+```python
+from modaic import AutoProgram
+
+program = AutoProgram.from_precompiled("raet/regspy", timeout=60)
+```
+
+Load a specific revision:
+
+```python
+from modaic import AutoProgram
+
+program = AutoProgram.from_precompiled("raet/regspy", rev="dev")
+program = AutoProgram.from_precompiled("raet/regspy", rev="v1.0")
+program = AutoProgram.from_precompiled("raet/regspy", rev="918ad95")
+```