Reddie – Autonomous AI Red-Teaming and GitHub PR Patching DevTool

Reddie is an autonomous DevSecOps tool that automatically discovers LLM application vulnerabilities, converts them into isolated pytest

reproduction test suites, synthesizes hardened prompt/guardrail patches, verifies them in a test sandbox, and opens a GitHub Pull Request with the fix — all in a single command.

📖

Not in Computer Science?Read our[Plain-English Non-Technical Explainer]for a simple, analogy-based breakdown.

pip install -e .

reddie --repo-path ./path/to/repo --export-html report.html --dry-run

export GROQ_API_KEY="gsk_..."
reddie --repo-path ./path/to/repo --export-html report.html --dry-run

export GROQ_API_KEY="gsk_..."
export GITHUB_TOKEN="ghp_..."
reddie --repo-path ./path/to/repo --github-repo owner/repo --export-html report.html

Add to .github/workflows/reddie-security.yml

:

name: 🛡️ Reddie Security Audit

on:
  pull_request:
    branches: [ main ]
  schedule:
    - cron: '0 2 * * *'  # Daily 2:00 AM UTC

jobs:
  security-audit:
    runs-on: ubuntu-latest
    permissions:
      contents: write
      pull-requests: write
    steps:
      - uses: actions/checkout@v4
      - name: Run Reddie
        uses: reddie-ai/reddie@v1
        with:
          repo-path: '.'
          github-token: ${{ secrets.GITHUB_TOKEN }}
          groq-key: ${{ secrets.GROQ_API_KEY }}
          export-html: 'report.html'
php
[RECON] ---> [REDTEAM] ---> [REPRODUCE] ---> [PATCH] ---> [VERIFY] ---> [PR]

reddie [OPTIONS]

  --repo-path PATH        Target repository to scan (default: .)
  --endpoint-url URL      Live LLM API endpoint to fuzz (default: mock://local)
  --github-repo REPO      GitHub repo for PR creation (e.g. owner/repo)
  --github-token TOKEN    GitHub PAT (or GITHUB_TOKEN env var)
  --groq-key KEY          Groq API key (or GROQ_API_KEY env var)
  --provider PROVIDER     LLM provider: groq | openrouter | openai (default: groq)
  --export-html PATH      Save executive HTML audit report
  --export-json PATH      Save structured JSON audit report
  --max-retries N         Max auto-patch retry attempts (default: 3)
  --dry-run               Audit locally, skip GitHub PR creation
  -v, --verbose           Enable debug logging
pytest -v
reddie/
├── main.py                  # CLI entry point
├── workflow.py              # LangGraph StateGraph orchestration
├── state.py                 # AgentSecurityState TypedDict
├── agents/
│   ├── recon.py             # Static analysis node
│   ├── red_team.py          # Adversarial fuzzing node
│   ├── reproduce.py         # PyTest generator node
│   ├── patcher.py           # LLM patch synthesis node
│   ├── verifier.py          # Sandbox test runner node
│   └── github_pr.py         # Git branch + PR creator node
├── tools/
│   ├── static_analyzer.py   # AST + regex prompt/tool extractor
│   ├── fuzzer_client.py     # HTTP fuzzer + heuristic evaluator
│   ├── llm_client.py        # Groq client: simulate, judge, patch
│   ├── reporter.py          # HTML + JSON OWASP report generator
│   ├── git_tools.py         # Git branch/commit/push + PyGithub PR
│   └── test_runner.py       # Subprocess pytest harness
├── tests/                   # Full test suite (13 tests)
├── assets/
│   └── banner.jpg
├── Dockerfile
├── docker-compose.yml
├── action.yml               # GitHub Action definition
└── NON_CS_EXPLAINER.md      # Plain-English guide

Built with LangGraph · Powered by Groq · Mapped to OWASP LLM Top 10 (2025)