Credits

Standing on tall shoulders

Think Stick is built with remarkable open technology. Thank you to every project below.

AI models on the stick

  • Qwen 3.5 (0.8B, 2B, 4B, 9B) — chat and vision models by Alibaba Cloud, Apache 2.0.
  • nomic-embed-text — semantic search embeddings by Nomic AI, Apache 2.0.
  • Kokoro — local text-to-speech voices, Apache 2.0.
  • Whisper-family speech recognition — local transcription, MIT.
  • Docling models — document layout and figure understanding by IBM, MIT.

Software

  • Ollama — local model runtime, MIT.
  • Node.js — application runtime, MIT.
  • Tesseract OCR & RapidOCR — reading scanned pages, Apache 2.0.
  • ImageMagick — image processing, ImageMagick License.

License texts ship on every stick. If you maintain one of these projects: thank you — you made a private AI for regular people possible.