Everstaff

C+ 71 completed
Other
cli / python · small
368
Files
44,523
LOC
4
Frameworks
9
Languages

Pipeline State

completed
Run ID
#395673
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
56.60
Framework unique
Isolation
Last stage change
2026-05-10 03:35:17
Deduplication group #50473
Member of a group with 8 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
Powered by Repobility — scan your code at https://repobility.com

AI Prompt

Create a full-stack platform for running autonomous AI agents, similar to Everstaff. I need the core functionality to support multi-LLM integration using providers like OpenAI, Anthropic, and Gemini, ideally via a library like LiteLLM. The system must feature a web UI that supports real-time WebSocket streaming for observability. Crucially, implement a Human-in-the-Loop (HITL) mechanism where agents pause and request human approval before critical actions. Also, include support for defining custom Python tools and allowing agents to delegate subtasks to child agents using a DAG-based workflow. The setup should be containerizable using a Dockerfile.
python fastapi react ai-agents llm websocket docker multi-agent cli web-app
Generated by gemma4:latest

Catalog Information

AI agents that know when to act and when to ask — autonomous by default, human-supervised when it counts.

Description

AI agents that know when to act and when to ask — autonomous by default, human-supervised when it counts.

Novelty

3/10

Tags

python fastapi react ai-agents llm websocket docker multi-agent cli web-app

Technologies

fastapi pydantic

Claude Models

claude-opus-4-6

Quality Score

C+
70.9/100
Structure
78
Code Quality
71
Documentation
68
Testing
85
Practices
59
Security
57
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (96% test-to-source ratio)
  • Code linting configured (eslint, ruff (possible))
  • Consistent naming conventions (snake_case)
  • Containerized deployment (Docker)

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • 9 files with critical complexity need refactoring
  • Potential hardcoded secrets in 1 files
  • 1987 duplicate lines detected \u2014 consider DRY refactoring
  • 4 'god files' with >500 LOC need decomposition

Recommendations

  • Add a LICENSE file (MIT recommended for open source)
  • Move hardcoded secrets to environment variables or a secrets manager

Security & Health

22.1h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Want fix-PRs on findings? Install Repobility's GitHub App · github.com/apps/repobility-bot
MIT
License
5.4%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
59.9%
javascript
15.9%
json
11.1%
markdown
8.7%
html
2.9%
yaml
0.5%
css
0.4%
text
0.4%
toml
0.2%

Frameworks

FastAPI React pytest Vite

Concepts (2)

Data scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · severity-and-effort ranking · https://repobility.com
auto_descriptionProject DescriptionAI agents that know when to act and when to ask — autonomous by default, human-supervised when it counts.80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/120030.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV