Jarvis

F 43 completed
Other
unknown / typescript · tiny
7
Files
330
LOC
0
Frameworks
3
Languages

Pipeline State

completed
Run ID
#397080
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_tiny
Novelty
10.53
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #48314
Member of a group with 1 similar repo(s) — canonical #108931 view group →
Top concepts (1)
Project Description
Source: Repobility analyzer · https://repobility.com

AI Prompt

Build me a basic coding agent similar to Jarvis. I want it written in TypeScript and should function as an LLM in a loop using raw HTTP calls to the OpenAI Chat Completions API. The agent needs to support multi-turn conversations with memory, and it must be able to interact with the file system by listing files, reading contents, and creating/editing files. It should also be able to run shell commands and operate autonomously until the task is complete. Please ensure it only uses Node.js standard library features.
typescript openai coding-agent node.js llm api-integration file-system command-line
Generated by gemma4:latest

Catalog Information

A coding agent built from scratch in ~180 lines of TypeScript. No frameworks, no SDKs — just raw HTTP calls to the OpenAI API.

Description

A coding agent built from scratch in ~180 lines of TypeScript. No frameworks, no SDKs — just raw HTTP calls to the OpenAI API.

Novelty

3/10

Tags

typescript openai coding-agent node.js llm api-integration file-system command-line

Claude Models

claude-opus-4-6

Quality Score

F
43.1/100
Structure
44
Code Quality
35
Documentation
32
Testing
0
Practices
71
Security
100
Dependencies
60

Strengths

  • Consistent naming conventions (snake_case)
  • 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

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)

Security & Health

4.6h
Tech Debt (E)
A
OWASP (100%)
FAIL
Quality Gate
B
Risk (22)
All rows scored by the Repobility analyzer (https://repobility.com)
ISC
License
0.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

typescript
62.3%
json
26.7%
markdown
11.0%

Frameworks

None detected

Concepts (1)

Findings curated by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Want fix-PRs on findings? Install Repobility's GitHub App · github.com/apps/repobility-bot
auto_descriptionProject DescriptionA coding agent built from scratch in 180 lines of TypeScript. No frameworks, no SDKs — just raw HTTP calls to the OpenAI API.80%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/121444.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV