Agent Os

C 61 completed
Other
unknown / typescript · small
77
Files
9,368
LOC
2
Frameworks
5
Languages

Pipeline State

completed
Run ID
#386118
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
61.68
Framework unique
Isolation
Last stage change
2026-05-10 03:34:36
Deduplication group #58699
Member of a group with 2 similar repo(s) — canonical #110403 view group →
Top concepts (2)
Project DescriptionWeb Backend
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/

AI Prompt

Build me a security-first, single-user, self-hosted personal AI agent using TypeScript and Express. I need it to have a robust architecture that includes a Gateway, an LLM Router supporting Anthropic, OpenAI, Gemini, and Ollama with automatic fallback, and a Tool Registry with about 40 tools. Key integrations must include Gmail (for searching, reading, drafting, etc.), Google Calendar (for listing, creating, updating, and deleting events), Telegram, and Slack. The system should also incorporate a Task Queue, Memory using SQLite, and support browser automation via Playwright.
typescript express ai-agent security llm google-api telegram slack automation self-hosted
Generated by gemma4:latest

Catalog Information

A security-first personal AI agent. Single-user, self-hosted, ~9K LOC.

Description

A security-first personal AI agent. Single-user, self-hosted, ~9K LOC.

Novelty

3/10

Tags

typescript express ai-agent security llm google-api telegram slack automation self-hosted

Technologies

anthropic express openai

Claude Models

claude-opus-4-6

Quality Score

C
60.8/100
Structure
62
Code Quality
70
Documentation
57
Testing
15
Practices
67
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Weaknesses

  • No tests found \u2014 high risk of regressions
  • 706 duplicate lines detected \u2014 consider DRY refactoring
  • 1 'god files' with >500 LOC need decomposition

Recommendations

  • Add a test suite \u2014 start with critical path integration tests
  • Add a linter configuration to enforce code style consistency
  • Address 26 TODO/FIXME items \u2014 consider tracking them as issues

Security & Health

10.6h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (3)
Generated by Repobility's multi-pass static-analysis pipeline (https://repobility.com)
MIT
License
1.2%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

typescript
71.2%
yaml
17.6%
markdown
8.9%
shell
1.6%
json
0.7%

Frameworks

Express esbuild

Concepts (2)

Open data · scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Repobility — same analyzer, your code, free for public repos · /scan/
auto_descriptionProject DescriptionA security-first personal AI agent. Single-user, self-hosted, 9K LOC.80%
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/110408.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV