v0.1.0

## [0.1.0] - 2025-09-02

### Added
- **Initial release of Shimmy** - The 5MB alternative to Ollama
- **Core inference engine** with llama.cpp backend integration
- **Full OpenAI API compatibility**:
  - `POST /v1/chat/completions` - OpenAI-compatible chat endpoint
  - `GET /v1/models` - List available models
- **Native Shimmy API**:
  - `POST /api/generate` - JSON generation with optional SSE streaming
  - `GET /ws/generate` - WebSocket streaming generation
  - `GET /health` - Health check endpoint
  - `GET /api/models` - Native model listing
- **CLI commands**:
  - `shimmy serve` - Start the inference server
  - `shimmy list` - List available models
  - `shimmy discover` - Discover models in filesystem
  - `shimmy generate` - Command-line text generation
  - `shimmy probe` - Test model loading
- **Model format support**:
  - GGUF models via llama.cpp integration
  - SafeTensors detection and guidance
  - Auto-discovery from filesystem
- **Template system**:
  - ChatML template support
  - Llama3 template support
  - OpenChat template support
- **Cross-platform support**:
  - Linux (x86_64, ARM64)
  - Windows (x86_64)
  - macOS (x86_64, ARM64)
- **Performance optimizations**:
  - 5.1MB single binary size
  - <100ms startup time
  - <50MB memory overhead
  - Release build with LTO and size optimization
- **Integration guides**:
  - VSCode Copilot configuration
  - Continue.dev setup
  - Cursor IDE integration
  - Generic OpenAI API client configuration
- **Package distribution**:
  - GitHub Releases (direct binary downloads)
  - crates.io (Rust package manager)
  - npm (Node.js wrapper package)
  - Docker Hub (container images)
  - PyPI (Python wrapper package)
- **Development infrastructure**:
  - Comprehensive test suite (27 unit tests + 4 integration tests)
  - GitHub Actions CI/CD pipeline
  - Cross-platform build automation
  - Multi-package-manager release automation
- **Documentation**:
  - Complete API documentation
  - Quick start guide (30-second setup)
  - Integration examples
  - Performance benchmarks
  - Architecture documentation

### Technical Details
- **Language**: Rust 2021 edition
- **Dependencies**: tokio, axum, llama-cpp-2, serde, clap
- **Features**: Optional `llama` feature for actual inference
- **License**: MIT (free forever)
- **Minimum supported Rust version**: 1.70+

### Performance Metrics
- **Binary size**: 5.1MB (vs Ollama's 680MB)
- **Startup time**: <100ms (vs Ollama's 5-10s)
- **Memory usage**: <50MB baseline (vs Ollama's 200MB+)
- **API compatibility**: 100% OpenAI compatibility (vs Ollama's partial)

### Free Forever Commitment
Shimmy is committed to being free forever with no asterisks, no "free for now" periods, and no pivot to paid services. The MIT license ensures this commitment is legally binding.

[Unreleased]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.6.1...HEAD
[2.6.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.6.0...v2.6.1
[2.6.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.5.0...v2.6.0
[2.5.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.4.2...v2.5.0
[2.4.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.4.0...v2.4.2
[2.4.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.4.0...v2.4.1
[2.4.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.3.3...v2.4.0
[2.3.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.2.1...v2.3.0
[2.2.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.2.0...v2.2.1
[2.2.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.1.0...v2.2.0
[2.1.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v2.0.0...v2.1.0
[2.0.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.9.0...v2.0.0
[1.9.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.8.1...v1.9.0
[1.8.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.8.0...v1.8.1
[1.8.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.7.4...v1.8.0
[1.7.4]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.7.3...v1.7.4
[1.7.3]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.7.2...v1.7.3
[1.7.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.7.0...v1.7.2
[1.7.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.6.0...v1.7.0
[1.6.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.6...v1.6.0
[1.5.6]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.5...v1.5.6
[1.5.5]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.4...v1.5.5
[1.5.4]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.3...v1.5.4
[1.5.3]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.2...v1.5.3
[1.5.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.1...v1.5.2
[1.5.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.5.0...v1.5.1
[1.5.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.4.2...v1.5.0
[1.4.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.4.1...v1.4.2
[1.4.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.4.0...v1.4.1
[1.4.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.3.5...v1.4.0
[1.3.5]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.3.3...v1.3.5
[1.3.3]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.3.2...v1.3.3
[1.3.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.3.1...v1.3.2
[1.3.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.2.0...v1.3.1
[1.2.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.1.0...v1.2.0
[1.1.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.0.1...v1.1.0
[1.0.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v1.0.0...v1.0.1
[1.0.0]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v0.1.2...v1.0.0
[0.1.2]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v0.1.1...v0.1.2
[0.1.1]: https://github.com/Michael-A-Kuykendall/shimmy/compare/v0.1.0...v0.1.1
[0.1.0]: https://github.com/Michael-A-Kuykendall/shimmy/releases/tag/v0.1.0