Today Superagentic AI publicly announcing SuperQode and SuperQE. They are open source tools that redefine how quality engineering works in the age of agentic software. SuperQode is the interactive TUI for exploratory quality engineering. SuperQE is the automation CLI for deep
evaluation testing and CI workflows. Together they create a new workflow where agents test agents, evidence replaces
assumptions, and humans remain in control.This release is the foundation for a new quality standard. AI can write code at unprecedented speed. We need quality systems that move just as fast.
What SuperQode is
SuperQode is a developer focused terminal UI built for agentic quality engineering. You connect a coding agent via the Agent Client Protocol,
explore your codebase, run adversarial testing, and review evidence. It feels like a live quality lab, but it is safe by
design.
- Interactive TUI for exploration and debugging
- Agent orchestration built in
- Role based testing for security, regression, API, full stack, and chaos
- Sandboxed workspace model that snapshots, tests, and reverts automatically
- Self hosted and privacy first by default
SuperQode is not just a UI. It is the execution harness for SuperQE. It provides the environment where deep testing can
happen without risking your repo.
What is SuperQE
SuperQE is the automation CLI that operationalizes agentic quality engineering. It runs in CI, in scheduled jobs, or as an ad hoc command.
SuperQE coordinates a team of testing agents with different personas, drives adversarial exploration, and produces Quality
Reports with evidence.
- Automation first CLI for quality engineering
- Multi agent testing to stress code from different angles
- Evidence based findings with reproducible steps
- Designed for CI and continuous validation
- Supports quick scans or deep evaluation runs
SuperQE is not test generation. It is adversarial validation. The goal is to break the code before users do, then prove
the fix with evidence.
Why we built this
AI coding agents are now writing production software. The quality systems around them did not evolve. Traditional
approaches assume deterministic behavior, slow change, and human authorship. That creates blind spots.
SuperQode and SuperQE close those gaps by enabling agentic QA. Agents can explore failure modes, detect emergent
behavior, and surface risk with reproducible evidence. This is a new quality paradigm, not a minor improvement.
How it works
- Snapshot the repository
- Sandbox all changes
- Run adversarial tests
- Generate Quality Reports
- Revert the repo by default
- Keep evidence and artifacts separately
This makes the system safe by default and powerful in practice.
Product demo
What you can do today
- Use SuperQode for interactive exploration
- Use SuperQE for automated quality runs
- Connect to ACP compatible coding agents
- Run deep evaluations with evidence and structured findings
Get started quickly via documentation or browse the GitHub repository.
Enterprise roadmap
Enterprise extends this foundation with deeper automation, verified fixes, richer CI outputs, and integration support.
The first integration is Moltbot, provided as an experimental self hosted option with secure, private local models.
Resources
- GitHub Repository: https://github.com/SuperagenticAI/superqode
- Documentation: https://superagenticai.github.io/superqode/
- Product Page: https://super-agentic.ai/superqode
This is the first public release of SuperQode and SuperQE. We are excited to share it with the community and begin building
the next generation of quality engineering workflows. If you build software with AI agents, we invite you to try it, break
things, and tell us what you find.
SuperQode and SuperQE. Redefining Quality Engineering for Agentic Software.