Our take
Maintaineda few commits in the last 90 days- Activity
- 32
- Community
- 14
- Issues
- 21
- Pull requests
- 20
+2 stars in the last 30 days
- Fewer contributors than 82% of the projects we track
ClickUi is a feature-rich desktop assistant with recent maintenance, but its single-contributor concentration and manual setup make it better suited to individual experimentation than an unreviewed team-wide dependency.
Good fit if
- You want a hotkey-accessible desktop chat that can use local Ollama or configured API models.
- You are comfortable setting up Python dependencies, API credentials, and, for voice features, Whisper and Kokoro.
- You want to explore voice interaction, web search, and file input in one Python application under the AGPL-3.0 license.
Look elsewhere if
- You need a project with a broader contributor base or regular releases. Recent commits indicate maintenance, but most code contributions come from one person and there has been no release in the past year.
- You need automated tests or CI to provide an established validation path. Neither is reported for this repository.
- You need polished voice controls or broader attachments today. The README lists voice interruption and multi-file attachment as unfinished ideas.
All health signals
| Last commit | 2026-09-07 (1 month ago) |
|---|---|
| Commits, last 90 days | 5 |
| Releases, last 12 months | 0 |
| Contributors | 3 (top contributor: 99% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 20 months |
Checked on 2026-10-09 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
429Forks
40Change since Nov 14, 2026: 0 stars·0 forks
Overview
ClickUi is a cross-platform Python desktop assistant designed to make AI available from a Ctrl+K shortcut. It combines a compact chat interface with voice interaction, allowing users to choose among local Ollama models and several API-backed providers.
The project is aimed at people who want an assistant alongside their normal computer workflow, rather than a standalone web chat. Search, file input, and optional speech and Sonos output extend the chat, though setup involves configuring dependencies and model credentials.
Key Features
- Opens and hides the chat interface with a configurable hotkey, Ctrl+K by default.
- Supports text chat and voice input using Whisper transcription and Kokoro speech output.
- Connects to Ollama, OpenAI, Google, Claude, Groq, and OpenRouter models.
- Performs Google searches and property-value lookups using browser automation and scraping.
- Accepts text, CSV, and spreadsheet file attachments through drag and drop.
- Can load local conversation history into a chat, with a corresponding increase in token use.
- Can route spoken responses to local audio or a Sonos speaker.
Use Cases
- A desktop user who wants quick access to an AI chat without switching to a browser can use the hotkey-driven interface.
- Someone with a configured local Ollama installation can use ClickUi as a desktop front end for local models.
- Users who prefer speaking to an assistant can try voice input and spoken replies after setting up Whisper and Kokoro.
- A user handling text or spreadsheet files can attach supported documents to ask a model about their contents.
- People researching current information can use the Google search integration, while recognizing it depends on browser automation and scraped results.
What you need
Detected in the repository
- Python (from requirements.txt)
License in plain words
AGPL-3.0network copyleft
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the license notice
- Share your changes: yes, the full source, also when people only use it over a network (e.g. as a hosted service)
- Includes an explicit patent grant from the contributors:
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Clone the repository, install the Conda and pip dependencies described in the README, configure .voiceconfig, then run:
python clickui.py
When the program reports that it is ready, use Ctrl+K to open the interface. See the README for installation and configuration details.
Alternatives
- Open-LLM-VTuber: Open-LLM-VTuber centers on voice conversations with a customizable Live2D avatar, while ClickUi offers hotkey-accessible voice and text chat without an avatar.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| ClickUi | Python | AGPL-3.0 | 427 | Maintained |
| Open-LLM-VTuber | Python | Other | 14k | Quiet |
Considerations
Voice mode depends on Whisper and Kokoro being installed and loaded, and the README warns that missing setup can cause runtime errors. API-backed models also require provider credentials; local model use depends on configuring Ollama. The documented easy installer is Windows-only, while manual setup uses Conda and pip.
The repository is marked maintained and has recent commits, but activity is concentrated in one contributor. There are no reported tests or CI, and no release in the past year. The README also identifies voice interruption, multi-file attachments, and easier cross-platform packaging as unfinished work. The AGPL-3.0 license should be reviewed for obligations before incorporating or distributing modified versions.
Found this useful?
Share it with someone who would like ClickUi.