Superior Quality-Oriented Agentic Software Development
Orchestrate, Validate, and Deploy Agentic Software with Unshakable Confidence.
Let agents break the code. Prove the fix. Ship with confidence.
📚 Documentation • 🐛 Report Bug • 💬 Discussions
SuperQE is the quality paradigm and automation CLI: Super Quality Engineering for Agentic AI. It uses QE coding agents to break and validate code written by coding agents. SuperQE can spawn a team of QE agents with different testing personas in a multi-agent setup to stress your code from many angles.
SuperQode is the agentic coding harness designed to drive the SuperQE process. It delivers a Superior and Quality Optimized Developer Experience as a TUI for interactive development, debugging, and exploratory QE. SuperQode can also be used as a general development harness beyond QE.
Note (Enterprise): Enterprise adds powerful automation, deep evaluation testing, and enterprise integrations (OpenClaw first; more bot integrations coming).
Watch the demo: SuperQode Demo
Primary (Recommended)
# Using uv (best performance)
uv tool install superqode
# Or using pip
pip install superqodeAlternate (No Python Required, SuperQode TUI Only)
Note: SuperQE (CLI) requires the Python install above (uv or pip).
# Using Homebrew (macOS/Linux)
brew install SuperagenticAI/superqode/superqode
# Using Curl script
curl -fsSL https://super-agentic.ai/install.sh | bashInteractive TUI (Explore)
cd your-project
superqodeAutomated QE (CI/CD)
cd your-project
superqe init
superqe run . --mode quick| Feature | Description |
|---|---|
| 🎯 Quality-First | Breaks and validates code, not generates it |
| 🛡️ Sandbox Execution | Destructive testing without production risk |
| 🤖 Multi-Agent QE | Cross-validation from multiple AI perspectives |
| 📋 Quality Reports | Forensic artifacts documenting findings |
| 👥 Human-in-the-Loop | All fixes are suggestions for human review |
| 🏠 Self-Hosted | BYOK, privacy-first, no SaaS dependency |
QE SESSION LIFECYCLE
━━━━━━━━━━━━━━━━━━━━
1. SNAPSHOT → Original code preserved
2. QE SANDBOX → Agents modify, test, break freely
3. REPORT → Document findings and fixes
4. REVERT → All changes removed automatically
5. ARTIFACTS → QRs and patches preserved
Your original code is ALWAYS restored.
For complete guides, configuration options, and API reference:
We welcome contributions! See CONTRIBUTING.md for guidelines.
git clone https://github.com/SuperagenticAI/superqode
cd superqode
uv pip install -e ".[dev]"
pytestAGPL-3.0 — Built by Superagentic AI for developers who care about code quality.