Tiny Notepad with Ollama
A sleek local notepad app powered by Ollama. Write notes, chat with open-source language models, and tweak generation settings. Built with a minimal Tkinter-based GUI. The goal of the project is to be an accessible, light weight version of open-webui capabilities available via a notepad app.
What is Tiny Notepad?
Tiny Notepad is a Python desktop app that allows you to:
- Write and save timestamped notes
- Load previous notes from a sidebar
- Interact with any locally installed Ollama model
- Adjust LLM generation parameters like temperature, top_p, top_k, etc.
Ideal for journaling, note-taking, or exploring how LLMs respond to prompts — all running entirely on your machine.
Features
-
Clean Tkinter GUI
-
Local-first: works offline with Ollama
-
Sidebar to browse saved notes
-
Real-time interaction with models (via Ollama API)
-
Editable generation settings:
temperaturetop_ptop_krepeat_penaltypresence_penaltyfrequency_penaltystopsequences
Installation
-
Install Python (>=3.7)
-
Install Tiny Notepad
pip install tiny-notepad
-
Install
ollama(required) Download Ollama and follow platform-specific installation instructions. -
Run a model via Ollama
Before using the app, make sure a model is pulled and running:
ollama pull llama3
ollama run llama3
OR
ollama serve
Usage
Once installed via pip, launch the app using:
tiny-notepad
The app will auto-check for Ollama and attempt to start
ollama serveif it's not already running.
Saved Notes
All notes are saved in a notes/ directory, auto-named like:
notes_2025-05-18_14-33-21.txt
You can browse and reopen them from the built-in sidebar.
Generation Parameters
| Parameter | Description | Default |
|---|---|---|
temperature |
Controls randomness (0 = deterministic, 2 = wild) | 0.7 |
top_p |
Nucleus sampling (probability threshold) | 0.9 |
top_k |
Limits to top-k tokens | 40 |
repeat_penalty |
Penalizes repeated tokens | 1.0 |
presence_penalty |
Encourages new topic exploration | 0.0 |
frequency_penalty |
Penalizes frequent tokens | 0.0 |
stop |
Comma-separated stop sequences to end generation | (custom) |
All parameters can be adjusted in the GUI in real time.
Tip
Pull and try other models using Ollama:
ollama pull mistral
ollama pull gemma
They will appear in the model dropdown after restarting the app.
License
MIT License © 2025 Ronald Wilson
Metadata
Release files for tiny-notepad 0.1.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| tiny_notepad-0.1.4.tar.gz | 7.6 kB | Without provenance | Details for tiny_notepad-0.1.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| tiny_notepad-0.1.4-py3-none-any.whl | Python 3 | none | any | Details for tiny_notepad-0.1.4-py3-none-any.whl |
Total release size: 15.4 kB
Release files / tiny_notepad-0.1.4.tar.gz
| Download URL | tiny_notepad-0.1.4.tar.gz |
|---|---|
| Size | 7.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
74b29af813a962b9c0cb843a2529d5be2a67ce5bfd13ae708fe7705f17eff099
|
|
BLAKE2b-256 checksum How to use checksums |
84822c7aa510d133fad6b906d97ff0aa5e0986b0f437cc52353eff440793ae2a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Release files / tiny_notepad-0.1.4-py3-none-any.whl
| Download URL | tiny_notepad-0.1.4-py3-none-any.whl |
|---|---|
| Size | 7.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
84d9e1d67f4a9c1fa16f8a3f81169b82baed9de8afd8f6be18ed0edb9a2bf19f
|
|
BLAKE2b-256 checksum How to use checksums |
851f36e9938fddd77c061e56bc1d99fb493b614a5351c3c18a95810d9983001f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Security for tiny-notepad 0.1.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.