How does Qodex memory actually work?
Qodex memory is a set of project files the agent can use across chats, scans, and test runs. It helps Qodex remember your app’s auth pattern, test accounts, workflow rules, known behavior, and previous findings.Always-loaded memory
Some memory is small and important enough to include in every agent turn.| File | Why it is always loaded |
|---|---|
project.md | Core project facts, stack, auth patterns, test accounts, and constraints. |
workflow_rules.md | Rules the agent should always follow. |
On-demand memory
Larger behavior notes are indexed and loaded only when relevant.| File | What it usually contains |
|---|---|
api_behavior.md | Endpoint behavior, payload patterns, and API observations. |
ui_behavior.md | Page behavior, selectors, UI flows, and browser observations. |
findings_digest.md | Condensed history of previous findings and resolutions. |
Why it is not traditional RAG
Qodex memory is file-based, not embedding-first. The agent reads named files or searches their text. This makes memory easier for humans to inspect, edit, and reason about.How memory stays bounded
Memory files have soft token caps. When a file gets too large, older sections can be summarized before new entries are added. The goal is to preserve useful facts without letting memory grow forever.Why this matters
Good memory helps Qodex:- Reuse the correct login flow.
- Avoid rediscovering known API and UI behavior.
- Respect project-specific rules.
- Explain why it made a testing decision.
- Avoid repeating past mistakes.
Next steps
Memory overview
Learn the memory system.
project.md
Write the most important project context.
Memory concept overview
See the conceptual model.
Editing and curating
Keep memory accurate over time.