Dashboard / Repos / Nexus

Nexus

B 81 completed
Ai Ml
cli / python · small
56
Files
9,409
LOC
1
Frameworks
6
Languages
OverviewFiles & MetricsGit ActivityCall GraphSecurityReports

Pipeline State

completed
Run ID
#363385
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
44.69
Framework unique
—
Isolation
—
Last stage change
2026-04-16 18:15:42
Deduplication group #47628
Member of a group with 1 similar repo(s) — canonical #27307 view group →
Top concepts (2)
Project DescriptionTesting
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/

🧪 Code Distillation

Browse all specs →
Function bodies →
0
Real LLM specs →
0
0.0% coverage
All specs →
0
LLM insights →
1

AI Prompt

Create a command-line documentation assistant, similar to Nexus, that uses AI to answer questions about a codebase. The tool needs to ingest a local repository into a searchable index. When a user asks a question, it must provide an answer that is grounded in the source code and include precise, inline citations showing the file path and line range for every claim. The system should utilize Docker Compose to manage services like an LLM provider (Ollama) and a vector store (ChromaDB). I need the core functionality to handle ingestion and querying via CLI commands.
python cli ai rag documentation docker llm codebase querying
Generated by gemma4:latest

Catalog Information

The nexus project is a code documentation assistant that uses AI to provide grounded answers and citations.

Description

Nexus is an AI-powered code documentation assistant that leverages the capabilities of large language models to generate accurate and informative documentation for developers. It utilizes a range of technologies, including ChromaDB and OpenAI, to provide grounded answers and citations. This tool aims to simplify the process of writing high-quality documentation by automating tasks such as information retrieval and formatting.

الوصف

هذا مشروع يعتمد على الذكاء الاصطناعي لتقديم مساعدات وثائقية للمبرمجين، يستخدم مجموعة من التكنولوجيات بما في ذلك ChromaDB و OpenAI لتقديم الإجابات المحددة والمصادر. هذا الأداة تسعى إلى تسهيل عملية كتابة الوثائق عالية الجودة عن طريق automation مهام مثل استرجاع المعلومات وتشكيلها.

Novelty

9/10

Tags

code-documentation ai-assistant documentation-generation information-retrieval citation-management

Technologies

chromadb ollama openai pydantic typer

Claude Models

claude-opus-4.6 claude-opus-4.5

Quality Score

B
81.4/100
Structure
75
Code Quality
90
Documentation
80
Testing
70
Practices
76
Security
100
Dependencies
60

Strengths

  • Good test coverage (74% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • 130 duplicate lines detected \u2014 consider DRY refactoring

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

4.3h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
Want fix-PRs on findings? Install Repobility's GitHub App · github.com/apps/repobility-bot
A
Risk (1)
MIT
License
2.5%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
50.4%
markdown
47.0%
yaml
1.1%
json
0.9%
toml
0.5%
text
0.2%

Frameworks

pytest

Concepts (2)

Data scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
All rows scored by the Repobility analyzer (https://repobility.com)
auto_descriptionProject DescriptionRAG-based code documentation assistant with grounded answers and citations.80%
auto_categoryTestingtesting70%

LLM Insights

AI‑powered code documentation assistant that provides grounded answers and citationsstructured_summary
info
purpose: AI‑powered code documentation assistant that provides grounded answers and citations
primary_domain: cli-tool
reference_quality70
reuse_potential: high

Quality Timeline

1 quality score recorded.

View File Metrics
Citation: Repobility (2026). State of AI-Generated Code. https://repobility.com/research/

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/87549.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV