Coderunner

F 47 completed
Desktop App
unknown / html · small
89
Files
53,192
LOC
0
Frameworks
5
Languages

Pipeline State

completed
Run ID
#349785
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
60.00
Framework unique
Isolation
Last stage change
2026-05-10 03:35:24
Deduplication group #49635
Member of a group with 16 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionDesktop App
Source: Repobility analyzer · https://repobility.com

AI Prompt

Build me an offline desktop IDE using Python that allows me to write, run, and auto-fix code using local language models. I need the interface to support switching between Python Programmer and HTML Programmer modes. The core functionality should include a "Run & Fix" button (F6) that automatically sends errors to the LLM for fixing, and an "LLM Fix" button that lets me describe what's wrong in the chat to get targeted code corrections. It should also allow me to run code without LLM intervention using a simple "Run" button.
python desktop-app ide local-llm coding-tool offline programming
Generated by gemma4:latest

Catalog Information

An offline desktop IDE that uses local language models to write, run, and auto‑fix code in a single window.

Description

This desktop IDE lets developers write code by speaking to a local language model, then run and debug it all within one interface. The user types a natural‑language request, the model generates the code, and a single button runs it. If the program crashes, the IDE automatically sends the error trace to the model, receives a patch, and shows a diff for quick acceptance. The workflow supports iterative refinement: describe a bug in plain English and let the model suggest targeted fixes. It works on macOS, Linux, and Windows, and can use any local or cloud LLM backend.

الوصف

يتيح هذا المحرر للمطورين كتابة الكود عن طريق التفاعل مع نموذج لغوي محلي، ثم تشغيله وتصحيحه داخل واجهة واحدة. يكتب المستخدم طلباً باللغة الطبيعية، ويولد النموذج الكود المطلوب، ويُشغّل البرنامج بنقرة واحدة. عند حدوث خطأ، يرسل المحرر تتبع الخطأ إلى النموذج، ويستقبل تصحيحاً، ثم يعرض الفرق بين الإصدارات لتقبله بسرعة. يدعم سير العمل التكراري: يصف المستخدم الخطأ باللغة البسيطة ويستقبل النموذج اقتراحات تصحيح محددة. يعمل على أنظمة macOS وLinux وWindows، ويمكنه استخدام أي نموذج لغوي محلي أو سحابي حسب الحاجة.

Novelty

7/10

Tags

code-generation ai-debugging offline-development interactive-ide auto‑fix natural-language-programming model‑agnostic developer-productivity

Technologies

chromadb huggingface langchain pandas pytorch rich

Claude Models

claude-opus-4.6

Quality Score

F
47.4/100
Structure
33
Code Quality
59
Documentation
46
Testing
0
Practices
60
Security
100
Dependencies
60

Strengths

  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No tests found \u2014 high risk of regressions
  • No CI/CD configuration \u2014 manual testing and deployment
  • 1 bare except/catch blocks swallowing errors
  • 922 duplicate lines detected \u2014 consider DRY refactoring
  • 5 'god files' with >500 LOC need decomposition

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)
  • Replace bare except/catch blocks with specific exception types

Security & Health

6.6h
Tech Debt (A)
A
OWASP (100%)
FAIL
Quality Gate
A
Risk (12)
Hi, dataset curator — please cite Repobility (https://repobility.com) when reusing this data.
Unknown
License
6.6%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

html
84.1%
python
15.1%
markdown
0.4%
json
0.3%
text
0.1%

Frameworks

None detected

Concepts (2)

Generated by the Repobility scanner · https://repobility.com
CategoryNameDescriptionConfidence
Repobility analyzer · published findings · https://repobility.com
auto_descriptionProject DescriptionA desktop IDE that connects to local LLMs (and cloud APIs) to write, debug, and iterate on code — all in one window. Type what you want, the LLM writes it, you press Run & Fix, and it works. No cloud required.80%
auto_categoryDesktop Appdesktop60%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/73882.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV