Skip to main content

SuperQode: Super Quality Engineering for Agentic Coding Teams

Project description

SuperQode Banner

SuperQode Logo

SuperQode

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.

PyPI Python CI License

Stars Forks Issues PRs

📚 Documentation🐛 Report Bug💬 Discussions


What is SuperQode and SuperQE?

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 (Moltbot first; more bot integrations coming).

Quick Start

Installation

Primary (Recommended)

# Using uv (best performance)
uv tool install superqode

# Or using pip
pip install superqode

Alternate (No Python Required)

# Using Homebrew (macOS/Linux)
brew install SuperagenticAI/superqode/superqode

# Using Curl script
curl -fsSL https://super-agentic.ai/install.sh | bash

Run SuperQode

Interactive TUI (Explore)

cd your-project
superqode

SuperQode TUI

Automated QE (CI/CD)

cd your-project
superqe init
superqe run . --mode quick

Key Features

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

How It Works

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.

Documentation

For complete guides, configuration options, and API reference:

📚 View Full Documentation →

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

git clone https://github.com/SuperagenticAI/superqode
cd superqode
uv pip install -e ".[dev]"
pytest

License

AGPL-3.0 — Built by Superagentic AI for developers who care about code quality.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

superqode-0.1.5.tar.gz (897.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

superqode-0.1.5-py3-none-any.whl (1.0 MB view details)

Uploaded Python 3

File details

Details for the file superqode-0.1.5.tar.gz.

File metadata

  • Download URL: superqode-0.1.5.tar.gz
  • Upload date:
  • Size: 897.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for superqode-0.1.5.tar.gz
Algorithm Hash digest
SHA256 594a58238986ab442c1570ff32b70ca671b866d7038f4c891732b06c425ad7e9
MD5 4d878052105b80bc3b8b163bac22dda9
BLAKE2b-256 9ae32d0e3148f55d1d05291d92d507f648d56502b21e65bf989228ac1fa83648

See more details on using hashes here.

File details

Details for the file superqode-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: superqode-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 1.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for superqode-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 0548ffc11507b3e7c2598413d64563a990520ff097ee84023a445b9400ff23d9
MD5 697306fb70452aaaa604d0155a221019
BLAKE2b-256 fb838a4d4fff26a1c6b8b71dd3cb1ec0452f86862d8782e3b2e4accb848476c2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page