diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0bb5081..56ae9d3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,55 @@
 # Changelog
 
+## 2.0.0 — 2025-11-06
+
+**Stable Release**: MLX Knife 2.0 replaces 1.x as the primary version. Full feature parity with 1.1.1 achieved plus major enhancements.
+
+### License Change
+
+- **MIT → Apache License 2.0**: Better patent protection, industry-standard licensing
+- See [MIGRATION.md](MIGRATION.md) for details on license change and user impact
+
+### Highlights
+
+- **Full 1.x Feature Parity**: All commands from 1.1.1 available (`list`, `show`, `pull`, `rm`, `run`, `server`, `health`)
+- **JSON API**: Machine-readable output for automation (`--json` flag on all commands)
+- **Enhanced Error Handling**: Structured errors with request IDs, logging levels, JSON logs
+- **Runtime Compatibility Checks**: Pre-flight validation prevents loading incompatible models
+- **Improved Stop Token Detection**: Multi-EOS support (MXFP4, Qwen, Llama)
+- **Better Human Output**: Improved formatting, relative timestamps, runtime status
+
+### Package Changes
+
+- **Package name**: `mlx-knife` (unchanged from 1.x)
+- **Primary command**: `mlxk` (replaces `mlxk2` from beta)
+- **Aliases**: `mlxk-json`, `mlxk2` (backwards compatibility)
+
+### Breaking Changes
+
+- **Lock file handling**: `mlxk rm` requires `--force` flag when models have active locks (safety improvement)
+- See [MIGRATION.md](MIGRATION.md) for complete migration guide from 1.x
+
+### Installation
+
+```bash
+# PyPI (recommended)
+pip install mlx-knife
+
+# GitHub release
+pip install https://github.com/mzau/mlx-knife/releases/download/v2.0.0/mlx_knife-2.0.0-py3-none-any.whl
+
+# Upgrade from 1.x
+pip install --upgrade mlx-knife
+```
+
+### Testing
+
+- 297 passed, 20 skipped (317 total tests)
+- Python 3.9-3.13 compatibility verified
+- Apple Silicon (M1/M2) tested
+
+---
+
 ## 2.0.0-beta.6 — 2025-10-22
 
 ### Fixed
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 0f985b2..3889865 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -6,19 +6,17 @@ First off, thank you for considering contributing to MLX Knife! It's people like
 
 We're a small team passionate about making MLX models accessible and easy to use on Apple Silicon. We welcome contributions from everyone who shares this vision.
 
-## 2.0 Alpha (JSON CLI) – Contributor Notes
+## 2.0 Stable – Contributor Notes
 
-- Code path: `mlxk2/` (entry points: `mlxk2`, `mlxk-json`).
-- Default output: human-friendly tables/text; pass `--json` to emit the exact JSON API (spec v0.1.2).
-- Supported commands: `list`, `health`, `show`, `pull`, `rm` (no server/run in 2.0 yet — use `mlxk` 1.x for those).
-- Tests: default suite is `tests_2.0/` (see `pytest.ini`); legacy `tests/` on demand.
-- Human output options:
-  - `list`: `--all` (all frameworks), `--health` (add column), `--verbose` (full org/model names).
-  - Compact default: MLX-only, compact names (strip `mlx-community/`), no Framework column.
-- Cache safety: tests use isolated temp caches; read-only ops are safe; coordinate `pull`/`rm` when using a shared user cache.
-- Spec discipline: JSON schema/spec changes require a version bump in `mlxk2/spec.py` (see CLAUDE.md and docs/).
-
-These 2.0 alpha changes do not affect 1.x (`mlx_knife/`) behavior.
+- **Code path:** `mlxk2/` (entry points: `mlxk`, `mlxk-json`, `mlxk2`)
+- **Default output:** Human-friendly tables/text; pass `--json` for machine-readable JSON API
+- **Full feature parity:** All commands available (`list`, `health`, `show`, `pull`, `rm`, `run`, `serve`)
+- **Tests:** Primary suite is `tests_2.0/` (see `pytest.ini`)
+- **Human output options:**
+  - `list`: `--all` (all frameworks), `--health` (add column), `--verbose` (full org/model names)
+  - Compact default: MLX-only, compact names (strip `mlx-community/`), no Framework column
+- **Cache safety:** Tests use isolated temp caches; read-only ops are safe; coordinate `pull`/`rm` when using a shared user cache
+- **Spec discipline:** JSON schema/spec changes require a version bump in `mlxk2/spec.py` (see docs/)
 
 
 ## How Can I Contribute?
@@ -241,10 +239,19 @@ Feel free to open an issue with the "question" label or start a discussion. We'r
 
 ## License
 
-- For 2.x (`mlxk2`, this branch): By contributing, you agree that your contributions will be licensed under the Apache License, Version 2.0.
-- For 1.x (`main`): By contributing, you agree that your contributions will be licensed under the MIT License.
+**Important:** MLX Knife 2.0+ is licensed under the **Apache License, Version 2.0**.
 
-Please ensure you have the right to contribute the code under these terms. We recommend including a Developer Certificate of Origin (DCO) “Signed-off-by” line in commits.
+By contributing to MLX Knife, you agree that:
+1. Your contributions will be licensed under the Apache License, Version 2.0
+2. You have the right to contribute the code under these terms
+3. You grant the project maintainers a perpetual, worldwide, non-exclusive, royalty-free license to use, reproduce, modify, and distribute your contributions
+
+**Legacy 1.x versions** (MIT License) are maintained in the `1.x-legacy` branch for reference only. All new contributions go to the main branch (Apache 2.0).
+
+We recommend including a Developer Certificate of Origin (DCO) "Signed-off-by" line in your commits:
+```bash
+git commit -s -m "Your commit message"
+```
 
 ---
 
diff --git a/MIGRATION.md b/MIGRATION.md
new file mode 100644
index 0000000..d2dd28d
--- /dev/null
+++ b/MIGRATION.md
@@ -0,0 +1,285 @@
+# Migration Guide: MLX Knife 1.x → 2.0
+
+This guide helps you transition from MLX Knife 1.x (MIT License) to 2.0 (Apache License 2.0).
+
+## License Change: MIT → Apache 2.0
+
+**Important:** MLX Knife 2.0 changes the license from MIT to Apache License 2.0.
+
+### What This Means for Users
+
+**Practical Impact:**
+- ✅ Still **free and open source**
+- ✅ Still **commercial use allowed**
+- ✅ Still **modification allowed**
+- ⚠️ **Attribution required** (include NOTICE file in distributions)
+- ⚠️ **Patent grant** (explicit patent protection for users)
+
+**Key Differences:**
+| Aspect | MIT (1.x) | Apache 2.0 (2.0+) |
+|--------|-----------|-------------------|
+| Use | ✅ Free | ✅ Free |
+| Modify | ✅ Allowed | ✅ Allowed |
+| Commercial | ✅ Allowed | ✅ Allowed |
+| Attribution | Optional | **Required** (NOTICE file) |
+| Patent Grant | Implicit | **Explicit** (better protection) |
+
+### Why Apache 2.0?
+
+1. **Better Patent Protection:** Explicit patent grant protects users from patent litigation
+2. **Industry Standard:** Used by major projects (Kubernetes, TensorFlow, Apache projects)
+3. **Clear Contribution Terms:** Explicit contributor licensing for future contributions
+
+### For Users: What You Need to Do
+
+**If you just use MLX Knife CLI:**
+- ✅ Nothing! Just upgrade: `pip install --upgrade mlx-knife`
+- The license change doesn't affect CLI usage
+
+**If you distribute MLX Knife in your product:**
+- ⚠️ Include the `LICENSE` file from the mlx-knife package
+- ⚠️ Include the `mlxk2/NOTICE` file in your distribution
+- Example: If bundling mlx-knife in a Mac app, include both files in your "Licenses" folder
+
+**If you're a 1.x user and prefer MIT:**
+- 🔒 Version 1.1.1 remains available under MIT License
+- Install specific version: `pip install mlx-knife==1.1.1`
+- Security updates will focus on 2.x (Apache 2.0)
+
+## Behavior Changes
+
+### `rm` Command: Lock File Handling
+
+The `rm` command now handles HuggingFace lock files more safely:
+
+**1.x Behavior:**
+```bash
+$ mlxk rm Phi-3-mini
+Delete entire model mlx-community/Phi-3-mini-4k-instruct-4bit? [y/N] y
+Model mlx-community/Phi-3-mini-4k-instruct-4bit completely deleted.
+Clean up cache files? [Y/n] y
+Cache files cleaned up (3 files).
+```
+
+**2.0 Behavior:**
+```bash
+# Models with active locks require --force
+$ mlxk rm Phi-3-mini
+Error: Model has active locks. Use --force to override.
+
+# With --force, deletion + lock cleanup happen automatically
+$ mlxk rm Phi-3-mini --force
+rm: mlx-community/Phi-3-mini-4k-instruct-4bit — deleted: Deleted entire model mlx-community/Phi-3-mini-4k-instruct-4bit
+```
+
+**Why the change?**
+- **Safety:** Prevents accidental deletion of models that may be in use
+- **Simplicity:** One confirmation instead of two separate prompts
+- **Clarity:** Explicit `--force` makes automation intent clear
+- **Automatic cleanup:** Lock files are cleaned silently (no separate prompt)
+
+**Note:** Lock file cleanup count is available in `--json` output (`lock_files_cleaned` field).
+
+**Migration for scripts:**
+- Interactive usage: No change needed (you'll get a clear error message if locks exist)
+- Automation: Add `--force` if your scripts delete models programmatically
+
+## New Features in 2.0
+
+### 1. JSON API for Automation
+
+All commands now support `--json` for machine-readable output:
+
+```bash
+mlxk list --json
+mlxk show Phi-3-mini --json
+mlxk rm Phi-3-mini --force --json
+```
+
+**Example:**
+```bash
+# Extract model names for scripting
+mlxk list --json | jq -r '.data.models[] | .name'
+
+# Check lock cleanup count
+mlxk rm test-model --force --json | jq '.data.lock_files_cleaned'
+```
+
+### 2. Enhanced Error Handling & Logging
+
+- **Structured errors** with request IDs for debugging
+- **Log levels:** `--log-level debug|info|warning|error`
+- **JSON logs:** `--log-json` or `MLXK2_LOG_JSON=1`
+- **Auto-redaction:** HF tokens and user paths automatically hidden
+
+```bash
+# Debug mode
+mlxk run Phi-3-mini "test" --log-level debug
+
+# JSON logs for production
+mlxk server --log-json --log-level info
+```
+
+### 3. Runtime Compatibility Checks
+
+Pre-flight validation catches issues before model loading:
+
+```bash
+$ mlxk show Phi-3-mini
+Model: Phi-3-mini-4k-instruct-4bit
+Health: healthy
+Runtime: compatible
+
+$ mlxk show legacy-model
+Model: legacy-model
+Health: healthy (files OK)
+Runtime: incompatible
+Reason: Legacy format not supported by mlx-lm
+```
+
+### 4. Better Stop Token Detection
+
+Fixed issues with multi-EOS models:
+- No more visible stop tokens (`<|end|>`)
+- No more "self-conversation" (model continuing after response)
+- Works with MXFP4, Qwen, Llama models
+
+### 5. Improved Human Output Formatting
+
+- Shorter model names (strip `mlx-community/` prefix by default)
+- Relative timestamps ("2 days ago")
+- Better alignment and readability
+- Use `--verbose` for full names and details
+
+## Command Compatibility
+
+| Command | 1.x | 2.0 | Notes |
+|---------|-----|-----|-------|
+| `mlxk list` | ✅ | ✅ | Improved formatting, add `--verbose` for full names |
+| `mlxk show <model>` | ✅ | ✅ | Added `runtime_compatible` field |
+| `mlxk pull <model>` | ✅ | ✅ | Better error messages |
+| `mlxk rm <model>` | ✅ | ⚠️ | Lock files require `--force` (safer) |
+| `mlxk run <model>` | ✅ | ✅ | Better stop token handling |
+| `mlxk server` | ✅ | ✅ | Added `--log-level`, `--log-json` |
+| `mlxk health` | ✅ | ✅ | Added runtime compatibility checks |
+
+## Package & Command Names
+
+- **PyPI Package:** `mlx-knife` (unchanged)
+- **Primary Command:** `mlxk` (unchanged)
+- **Aliases:** `mlxk-json`, `mlxk2` (for backwards compatibility)
+
+```bash
+# All three commands are identical
+mlxk --version       # → 2.0.0
+mlxk-json --version  # → 2.0.0
+mlxk2 --version      # → 2.0.0
+```
+
+## Installation & Upgrade
+
+### Upgrade from 1.x
+
+```bash
+# Simple upgrade
+pip install --upgrade mlx-knife
+
+# Verify version
+mlxk --version  # Should show: mlxk 2.0.0
+```
+
+### Fresh Installation
+
+```bash
+# Install from PyPI
+pip install mlx-knife
+
+# Or from GitHub release
+pip install https://github.com/mzau/mlx-knife/releases/download/v2.0.0/mlx_knife-2.0.0-py3-none-any.whl
+```
+
+### Staying on 1.x (MIT License)
+
+```bash
+# Pin to 1.x version
+pip install mlx-knife==1.1.1
+
+# Or in requirements.txt
+mlx-knife==1.1.1
+```
+
+## Data & Cache Compatibility
+
+✅ **Your model cache is 100% compatible**
+
+- Same HuggingFace cache: `~/.cache/huggingface/hub`
+- All 1.x models work in 2.0 immediately
+- No re-download required
+- No migration needed
+
+## Testing Before Upgrade
+
+```bash
+# Test 2.0 in a virtual environment
+python3 -m venv test-mlxk2
+source test-mlxk2/bin/activate
+pip install mlx-knife
+
+# Verify your workflow
+mlxk list
+mlxk run YourFavoriteModel "test prompt"
+mlxk rm test-model --force  # Note: --force for locks
+
+# If satisfied, upgrade
+deactivate
+pip install --upgrade mlx-knife
+```
+
+## Upgrade Checklist for Automation Scripts
+
+If you have scripts using mlxk:
+
+- [ ] **Add `--force` to `mlxk rm` commands** (if deleting programmatically)
+- [ ] **Replace output parsing with `--json`** (don't parse human output)
+- [ ] **Test in virtual environment first**
+- [ ] **Update error handling** for structured error responses
+- [ ] **Consider `--log-json`** for production logging
+
+## FAQ
+
+**Q: Will my 1.x scripts break?**
+A: Only `mlxk rm` scripts that delete models with active locks without `--force`. This is a safety improvement.
+
+**Q: Why does `rm` need `--force` for locks?**
+A: To prevent accidental deletion of models that may be in use. Locks indicate active downloads or usage.
+
+**Q: Can I still use interactive deletion?**
+A: Yes! Without `--force`, you'll get clear error messages about locks and can decide whether to use `--force`.
+
+**Q: Do I need to re-download models?**
+A: No! All cached models from 1.x work immediately.
+
+**Q: What about the web chat interface?**
+A: `simple_chat.html` works with both 1.x and 2.0 (OpenAI API unchanged).
+
+**Q: Can I contribute to 1.x?**
+A: 1.x is in maintenance mode. New contributions go to 2.x (Apache 2.0).
+
+**Q: Where's the 1.x source code?**
+A: The `1.x-legacy` branch contains the final MIT version (1.1.1).
+
+## Need Help?
+
+- **Issues:** https://github.com/mzau/mlx-knife/issues
+- **Discussions:** https://github.com/mzau/mlx-knife/discussions
+- **Documentation:** https://github.com/mzau/mlx-knife
+
+## Timeline
+
+- **1.1.1 (MIT):** Final 1.x release - September 2025
+- **2.0.0 (Apache 2.0):** Stable release - November 2025
+- **1.x Support:** Security fixes only
+
+---
+
+**The BROKE Team** 🦫
diff --git a/README.md b/README.md
index 18ecdc8..9c36073 100644
--- a/README.md
+++ b/README.md
@@ -1,15 +1,15 @@
-# <img src="https://github.com/mzau/mlx-knife/raw/main/broke-logo.png" alt="BROKE Logo" width="60" style="vertical-align: middle;"> MLX-Knife 2.0.0-beta.6
+# <img src="https://github.com/mzau/mlx-knife/raw/main/broke-logo.png" alt="BROKE Logo" width="60" style="vertical-align: middle;"> MLX-Knife 2.0
 
 <p align="center">
-  <img src="https://github.com/mzau/mlx-knife/raw/feature/2.0.0-alpha.1/mlxk-demo.gif" alt="MLX Knife Demo" width="900">
+  <img src="https://github.com/mzau/mlx-knife/raw/main/mlxk-demo.gif" alt="MLX Knife Demo" width="900">
 </p>
 
-**Stable Version: 1.1.1**
+**Current Stable Version: 2.0.0**
 
-[![GitHub Release](https://img.shields.io/badge/version-2.0.0--beta.6-orange.svg)](https://github.com/mzau/mlx-knife/releases)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![GitHub Release](https://img.shields.io/badge/version-2.0.0-green.svg)](https://github.com/mzau/mlx-knife/releases)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
 [![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
-[![Apple Silicon](https://img.shields.io/badge/Apple%20Silicon-M1%2FM2%2FM3-green.svg)](https://support.apple.com/en-us/HT211814)
+[![Apple Silicon](https://img.shields.io/badge/Apple%20Silicon-green.svg)](https://support.apple.com/en-us/HT211814)
 [![MLX](https://img.shields.io/badge/MLX-Latest-orange.svg)](https://github.com/ml-explore/mlx)
 
 
@@ -25,7 +25,7 @@
 - **Privacy & Network**: No background network or telemetry; only explicit Hugging Face interactions when you run pull or the experimental push.
 
 ### Requirements
-- macOS with Apple Silicon (M1/M2/M3)
+- macOS with Apple Silicon
 - Python 3.9+ (native macOS version or newer)
 - 8GB+ RAM recommended + RAM to run LLM
 
@@ -39,14 +39,24 @@ MLX Knife has been comprehensively tested and verified on:
 
 ## Installation
 
-### Beta Release Installation (Recommended)
+### Via PyPI (Recommended)
 
 ```bash
-# Install latest beta release directly from GitHub
-pip install https://github.com/mzau/mlx-knife/releases/download/v2.0.0-beta.6/mlxk_json-2.0.0b6-py3-none-any.whl
+# Install stable release from PyPI
+pip install mlx-knife
 
 # Verify installation
-mlxk2 --version  # → mlxk2 2.0.0b6
+mlxk --version  # → mlxk 2.0.0
+```
+
+### Via GitHub Release
+
+```bash
+# Install latest release from GitHub
+pip install https://github.com/mzau/mlx-knife/releases/download/v2.0.0/mlx_knife-2.0.0-py3-none-any.whl
+
+# Verify installation
+mlxk --version  # → mlxk 2.0.0
 ```
 
 ### Development Installation
@@ -55,13 +65,12 @@ mlxk2 --version  # → mlxk2 2.0.0b6
 # Clone and install from source
 git clone https://github.com/mzau/mlx-knife.git
 cd mlx-knife
-git checkout feature/2.0.0-alpha.1
 
 # Install with all development dependencies (required for testing and code quality)
 pip install -e ".[dev,test]"
 
 # Verify installation
-mlxk2 --version  # → mlxk2 2.0.0-beta.6
+mlxk --version  # → mlxk 2.0.0
 
 # Run tests and quality checks (before committing)
 pytest -v
@@ -71,29 +80,33 @@ mypy mlxk2/
 
 **Note:** For minimal user installation without dev tools: `pip install -e .`
 
+### Migrating from 1.x
+
+If you're upgrading from MLX Knife 1.x, see [MIGRATION.md](MIGRATION.md) for important information about the license change (MIT → Apache 2.0) and behavior changes.
+
 
 ## Quick Start
 
 ```bash
 # List models (human-readable)
-mlxk2 list
-mlxk2 list --health
-mlxk2 list --verbose --health
+mlxk list
+mlxk list --health
+mlxk list --verbose --health
 
 # Check cache health
-mlxk2 health
+mlxk health
 
 # Show model details
-mlxk2 show "mlx-community/Phi-3-mini-4k-instruct-4bit"
+mlxk show "mlx-community/Phi-3-mini-4k-instruct-4bit"
 
 # Pull a model
-mlxk2 pull "mlx-community/Llama-3.2-3B-Instruct-4bit"
+mlxk pull "mlx-community/Llama-3.2-3B-Instruct-4bit"
 
 # Run interactive chat
-mlxk2 run "Phi-3-mini" -c
+mlxk run "Phi-3-mini" -c
 
 # Start OpenAI-compatible server
-mlxk2 serve --port 8080
+mlxk serve --port 8080
 ```
 
 
@@ -124,9 +137,9 @@ All commands support both human-readable and JSON output (`--json` flag) for aut
 All commands support JSON output via `--json` flag:
 
 ```bash
-mlxk2 list --json | jq '.data.models[].name'
-mlxk2 health --json | jq '.data.summary'
-mlxk2 show "Phi-3-mini" --json | jq '.data.model'
+mlxk list --json | jq '.data.models[].name'
+mlxk health --json | jq '.data.summary'
+mlxk show "Phi-3-mini" --json | jq '.data.model'
 ```
 
 **Response Format:**
@@ -143,7 +156,7 @@ mlxk2 show "Phi-3-mini" --json | jq '.data.model'
 
 #### List Models
 ```bash
-mlxk2 list --json
+mlxk list --json
 # Output:
 {
   "status": "success",
@@ -172,7 +185,7 @@ mlxk2 list --json
 
 #### Health Check
 ```bash
-mlxk2 health --json
+mlxk health --json
 # Output:
 {
   "status": "success",
@@ -194,7 +207,7 @@ mlxk2 health --json
 
 #### Show Model Details
 ```bash
-mlxk2 show "Phi-3-mini" --json --files
+mlxk show "Phi-3-mini" --json --files
 # Output (simplified):
 {
   "status": "success",
@@ -228,9 +241,9 @@ mlxk2 show "Phi-3-mini" --json --files
 All commands support `@hash` syntax for specific model versions:
 
 ```bash
-mlxk2 health "Qwen3@e96" --json     # Check specific hash
-mlxk2 show "model@3df9bfd" --json   # Short hash matching
-mlxk2 rm "Phi-3@e967" --json --force  # Delete specific version
+mlxk health "Qwen3@e96" --json     # Check specific hash
+mlxk show "model@3df9bfd" --json   # Short hash matching
+mlxk rm "Phi-3@e967" --json --force  # Delete specific version
 ```
 
 ### Integration Examples
@@ -238,39 +251,39 @@ mlxk2 rm "Phi-3@e967" --json --force  # Delete specific version
 #### Broke-Cluster Integration
 ```bash
 # Get available model names for scheduling
-MODELS=$(mlxk2 list --json | jq -r '.data.models[].name')
+MODELS=$(mlxk list --json | jq -r '.data.models[].name')
 
 # Check cache health before deployment
-HEALTH=$(mlxk2 health --json | jq '.data.summary.healthy_count')
+HEALTH=$(mlxk health --json | jq '.data.summary.healthy_count')
 if [ "$HEALTH" -eq 0 ]; then
     echo "No healthy models available"
     exit 1
 fi
 
 # Download required models
-mlxk2 pull "mlx-community/Phi-3-mini-4k-instruct-4bit" --json
+mlxk pull "mlx-community/Phi-3-mini-4k-instruct-4bit" --json
 ```
 
 #### CI/CD Pipeline Usage
 ```bash
 # Verify model integrity in CI
-mlxk2 health --json | jq -e '.data.summary.unhealthy_count == 0'
+mlxk health --json | jq -e '.data.summary.unhealthy_count == 0'
 
 # Clean up CI artifacts
-mlxk2 rm "test-model-*" --json --force
+mlxk rm "test-model-*" --json --force
 
 # Pre-warm cache for deployment
-mlxk2 pull "production-model" --json
+mlxk pull "production-model" --json
 ```
 
 #### Model Management Automation
 ```bash
 # Find models by pattern
-LARGE_MODELS=$(mlxk2 list --json | jq -r '.data.models[] | select(.name | contains("30B")) | .name')
+LARGE_MODELS=$(mlxk list --json | jq -r '.data.models[] | select(.name | contains("30B")) | .name')
 
 # Show detailed info for analysis
 for model in $LARGE_MODELS; do
-    mlxk2 show "$model" --json --config | jq '.data.model_config'
+    mlxk show "$model" --json --config | jq '.data.model_config'
 done
 ```
 
@@ -282,10 +295,10 @@ MLX Knife provides rich human-readable output by default (without `--json` flag)
 ### Basic Usage
 
 ```bash
-mlxk2 list
-mlxk2 list --health
-mlxk2 health
-mlxk2 show "mlx-community/Phi-3-mini-4k-instruct-4bit"
+mlxk list
+mlxk list --health
+mlxk health
+mlxk show "mlx-community/Phi-3-mini-4k-instruct-4bit"
 ```
 
 ### List Filters
@@ -315,21 +328,21 @@ The `--health` flag adds health status information to the output:
 
 ```bash
 # Compact health view
-mlxk2 list --health
+mlxk list --health
 # Output:
 # Name                    | Hash    | Size   | Modified | Type | Health
 # Llama-3.2-3B-Instruct   | a1b2c3d | 2.1GB  | 2d ago   | chat | healthy
 # Qwen2-7B-Instruct       | 1a2b3c4 | 4.8GB  | 3d ago   | chat | healthy*
 
 # Verbose health view with details
-mlxk2 list --verbose --health
+mlxk list --verbose --health
 # Output:
 # Name                    | Hash    | Size   | Modified | Framework | Type | Integrity | Runtime | Reason
 # Llama-3.2-3B-Instruct   | a1b2c3d | 2.1GB  | 2d ago   | MLX       | chat | healthy   | yes     | -
 # Qwen2-7B-Instruct       | 1a2b3c4 | 4.8GB  | 3d ago   | PyTorch   | chat | healthy   | no      | Incompatible: PyTorch
 
 # All frameworks with health status
-mlxk2 list --all --health
+mlxk list --all --health
 # Output:
 # Name                    | Hash    | Size   | Modified | Framework | Type    | Health
 # Llama-3.2-3B-Instruct   | a1b2c3d | 2.1GB  | 2d ago   | MLX       | chat    | healthy
@@ -355,16 +368,16 @@ Control verbosity with `--log-level` (server mode):
 
 ```bash
 # Default: Show startup, model loading, and errors
-mlxk2 serve --log-level info
+mlxk serve --log-level info
 
 # Quiet: Only warnings and errors
-mlxk2 serve --log-level warning
+mlxk serve --log-level warning
 
 # Silent: Only errors
-mlxk2 serve --log-level error
+mlxk serve --log-level error
 
 # Verbose: All logs including HTTP requests
-mlxk2 serve --log-level debug
+mlxk serve --log-level debug
 ```
 
 **Log Level Behavior:**
@@ -379,10 +392,10 @@ Enable structured JSON output for log aggregation tools:
 
 ```bash
 # JSON logs (recommended - CLI flag)
-mlxk2 serve --log-json
+mlxk serve --log-json
 
 # JSON logs (alternative - environment variable)
-MLXK2_LOG_JSON=1 mlxk2 serve
+MLXK2_LOG_JSON=1 mlxk serve
 ```
 
 **Note:** `--log-json` also formats Uvicorn access logs as JSON for consistent output.
@@ -435,14 +448,14 @@ MLX-Knife 2.0 respects standard HuggingFace cache structure and practices:
 ### Example Safe Workflow
 ```bash
 # Check what's in cache (always safe)
-mlxk2 list --json | jq '.data.count'
+mlxk list --json | jq '.data.count'
 
 # Maintenance window - coordinate with team
-mlxk2 rm "corrupted-model" --json --force
-mlxk2 pull "replacement-model" --json
+mlxk rm "corrupted-model" --json --force
+mlxk pull "replacement-model" --json
 
 # Back to normal operations
-mlxk2 health --json | jq '.data.summary'
+mlxk health --json | jq '.data.summary'
 ```
 
 
@@ -450,7 +463,7 @@ mlxk2 health --json | jq '.data.summary'
 
 ### `clone` - Model Workspace Creation
 
-`mlxk2 clone` is a hidden alpha feature. Enable with `MLXK2_ENABLE_ALPHA_FEATURES=1`. It creates a local workspace from a cached model for modification and development.
+`mlxk clone` is a hidden alpha feature. Enable with `MLXK2_ENABLE_ALPHA_FEATURES=1`. It creates a local workspace from a cached model for modification and development.
 
 - Creates isolated workspace from cached models
 - Supports APFS copy-on-write optimization on same-volume scenarios
@@ -463,12 +476,12 @@ Example:
 export MLXK2_ENABLE_ALPHA_FEATURES=1
 
 # Clone model to workspace
-mlxk2 clone org/model ./workspace
+mlxk clone org/model ./workspace
 ```
 
 ### `push` - Upload to Hub
 
-`mlxk2 push` is a hidden alpha feature. Enable with `MLXK2_ENABLE_ALPHA_FEATURES=1`. It uploads a local folder to a Hugging Face model repository using `huggingface_hub/upload_folder`.
+`mlxk push` is a hidden alpha feature. Enable with `MLXK2_ENABLE_ALPHA_FEATURES=1`. It uploads a local folder to a Hugging Face model repository using `huggingface_hub/upload_folder`.
 
 - Requires `HF_TOKEN` (write-enabled).
 - Default branch: `main` (explicitly override with `--branch`).
@@ -491,7 +504,7 @@ Example:
 export MLXK2_ENABLE_ALPHA_FEATURES=1
 
 # Use push command
-mlxk2 push --private ./workspace org/model --create --commit "init"
+mlxk push --private ./workspace org/model --create --commit "init"
 ```
 
 These features are not final and may change or be removed in future releases.
@@ -571,6 +584,6 @@ Apache License 2.0 — see `LICENSE` (root) and `mlxk2/NOTICE`.
 
 <p align="center">
   <b>Made with ❤️ by The BROKE team <img src="broke-logo.png" alt="BROKE Logo" width="30" style="vertical-align: middle;"></b><br>
-  <i>Version 2.0.0-beta.6 | October 2025</i><br>
+  <i>Version 2.0.0 | November 2025</i><br>
   <a href="https://github.com/mzau/broke-cluster">🔮 Next: BROKE Cluster for multi-node deployments</a>
 </p>
diff --git a/mlxk2/__init__.py b/mlxk2/__init__.py
index d8d520a..76fd534 100644
--- a/mlxk2/__init__.py
+++ b/mlxk2/__init__.py
@@ -7,4 +7,4 @@ import warnings
 # Issue parity with 1.1.0 (Issue #22)
 warnings.filterwarnings('ignore', message='urllib3 v2 only supports OpenSSL 1.1.1+')
 
-__version__ = "2.0.0b6"
+__version__ = "2.0.0"
diff --git a/pyproject.toml b/pyproject.toml
index 35dc187..872b4cb 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -3,9 +3,9 @@ requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "mlxk-json"
+name = "mlx-knife"
 dynamic = ["version"]
-description = "MLX-Knife 2.0 - JSON-first model management for automation"
+description = "HuggingFace model management for MLX on Apple Silicon"
 readme = "README.md"
 requires-python = ">=3.9"
 license = {text = "Apache-2.0"}
@@ -13,12 +13,12 @@ authors = [
     {name = "The BROKE team", email = "broke@gmx.eu"},
 ]
 classifiers = [
-    "Development Status :: 3 - Alpha",
+    "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Developers",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10", 
+    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
@@ -38,6 +38,7 @@ dependencies = [
 ]
 
 [project.scripts]
+mlxk = "mlxk2.cli:main"
 mlxk-json = "mlxk2.cli:main"
 mlxk2 = "mlxk2.cli:main"