Jcode

C 61 completed
Cli Tool
unknown / java · tiny
28
Files
2,132
LOC
0
Frameworks
6
Languages

Pipeline State

completed
Run ID
#298793
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
52.25
Framework unique
Isolation
Last stage change
2026-05-10 03:34:14
Deduplication group #51740
Member of a group with 12 similar repo(s) — canonical #22925 view group →
Top concepts (4)
CLI ToolConfigurationDatabaseFile Management
Repobility · open methodology · https://repobility.com/research/

AI Prompt

Create a lightweight, terminal-based AI coding agent similar to jcode. I want it to function as an interactive coding assistant that connects to local LLMs like LM Studio and Ollama. Key features must include an interactive REPL, tool use capabilities (allowing it to read, write, edit files, run bash commands, grep, and find files), and automatic planning for complex tasks. It should also support a readonly mode and a one-shot mode for simple prompts. Since it's local-first, it shouldn't require cloud API keys.
java cli ai-agent terminal llm local-llm tool-use coding-assistant bash
Generated by gemma4:latest

Catalog Information

jcode is a lightweight, terminal-based AI coding agent that connects to local LLMs for an interactive coding assistant.

Description

jcode is a terminal-based AI coding agent powered by local LLMs. It connects to providers like LM Studio and Ollama, giving you a coding assistant in your terminal with full filesystem access and automatic planning. The agent has various features, including an interactive REPL, tool use, automatic planning, readonly mode, one-shot mode, and local-first functionality.

الوصف

يعد jcode مساعدًا لكتابة الكود عبر الوسائط التفاعلية في المجلدات المحلية، يعتمد على أجهزة LLM المحلية. يصل إلى مزودين مثل LM Studio و Ollama، مما يعطي لك مساعدًا للكتابة في المجلدات المحلية مع إمكانية الوصول الكامل للملفات والتنفيذ التلقائي. يحتوي المساعد على العديد من الميزات، بما في ذلك REPL التفاعلي، استخدام أدوات، التخطيط التلقائي، وضع القراءة فقط، ووضع واحد-المرة، وفункциوية أولى المحلية.

Novelty

7/10

Tags

interactive-coding-assistant local-lms filesystem-access automatic-planning readonly-mode oneshot-mode local-first

Claude Models

claude-opus-4.6

Quality Score

C
61.1/100
Structure
54
Code Quality
83
Documentation
57
Testing
0
Practices
74
Security
100
Dependencies
80

Strengths

  • Consistent naming conventions (PascalCase)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Weaknesses

  • No tests found \u2014 high risk of regressions
  • No CI/CD configuration \u2014 manual testing and deployment

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

Security & Health

5.1h
Tech Debt (D)
High
DORA Rating
A
OWASP (100%)
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/
PASS
Quality Gate
A
Risk (6)
MIT
License
1.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

java
85.4%
xml
7.0%
markdown
5.6%
json
0.9%
ruby
0.8%
text
0.2%

Frameworks

None detected

Symbols

variable261
method81
constant37
class23
function10
interface2
enum1

Concepts (4)

Per-row analysis by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · code-quality intelligence platform · https://repobility.com
auto_categoryCLI Toolcli60%
business_logicConfigurationDetected from 5 related files50%
business_logicDatabaseDetected from 5 related files50%
business_logicFile ManagementDetected from 4 related files50%

Quality Timeline

1 quality score recorded.

View File Metrics
All rows scored by the Repobility analyzer (https://repobility.com)

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/22592.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV