How to Give Claude Code Persistent Project Memory
Claude Code is powerful session-by-session. RAAV gives it durable product truth, tasks, and audit trail so every session starts from the same playbook.
The session amnesia problem
Claude Code can ship a feature in one session and forget the product context in the next. Founders re-explain the app. Agents re-discover the same files. Verification status lives in chat scrollback.
Persistent project memory fixes that without replacing Claude Code as your coding agent.
What to store in shared memory
At minimum: product brief, active goals, open requirements, prioritized tickets, branch lanes, and claims. When an agent runs `raav submit`, record files touched, summary, verification command, and risks.
Founders review confirmed vs inferred fields in the product handbook — not raw diffs.
Setup in one repo
Install the RAAV CLI, run `raav init`, and paste the onboarding prompt from the install page into Claude Code. Seed product memory with onboard-and-plan, then pull scoped work with `raav next`.
See the install guide for the exact prompt and verification steps.
When memory beats another prompt
Use RAAV when multiple sessions touch the same launch, when two agents might collide on files, or when a founder needs an audit trail for handoffs and investors.
For PM onboarding without reading every file, pair memory with the codebase onboarding use case.