Thukiwin
C+ 76 completed
Other
desktop_app / typescript · small
129
Files
29,005
LOC
4
Frameworks
11
Languages
Pipeline State
completedRun ID
#1540728Phase
doneProgress
0%Started
2026-04-16 20:16:35Finished
2026-04-16 20:16:35LLM tokens
0Pipeline Metadata
Stage
CatalogedDecision
proceedNovelty
55.00Framework unique
—Isolation
—Last stage change
2026-05-10 03:34:40Deduplication group #51000
Repobility (the analyzer behind this table) · https://repobility.com
🧪 Code Distillation
Browse all specs →AI Prompt
Create a desktop application for Windows, similar to a floating AI secretary, that runs completely locally. I need it to be summonable by double-tapping Ctrl from any application, including fullscreen ones. Key features should include context-aware querying where users can highlight text to pre-fill the prompt, and the ability to capture the screen as context. The application should use local AI models, ideally integrating with Ollama, and store conversation history in a local SQLite database. Please use React and Tauri for the frontend/desktop structure, and ensure it's built with TypeScript.
typescript react tauri desktop-app windows ai local ollama sqlite rust
Generated by gemma4:latest
Catalog Information
Create a desktop application for Windows, similar to a floating AI secretary, that runs completely locally. I need it to be summonable by double-tapping Ctrl from any application, including fullscreen ones. Key features should include context-aware querying where users can highlight text to pre-fill the prompt, and the ability to capture the screen as context. The application should use local AI models, ideally integrating with Ollama, and store conversation history in a local SQLite database. P
Tags
typescript react tauri desktop-app windows ai local ollama sqlite rust
Quality Score
C+
76.2/100
Structure
81
Code Quality
63
Documentation
84
Testing
85
Practices
72
Security
82
Dependencies
90
Strengths
- CI/CD pipeline configured (github_actions)
- Good test coverage (53% test-to-source ratio)
- Code linting configured (eslint)
- Good security practices — no major issues detected
- Containerized deployment (Docker)
- Properly licensed project
Weaknesses
- Potential hardcoded secrets in 1 files
- 2800 duplicate lines detected — consider DRY refactoring
- 7 'god files' with >500 LOC need decomposition
Recommendations
- Move hardcoded secrets to environment variables or a secrets manager
Languages
Frameworks
React Tauri Vitest Vite
Symbols
function466
variable332
constant126
interface35
struct26
type_alias19
extension7
method7
class4
enum4
Embed Badge
Add to your README:
