Persis gives Claude persistent memory that learns from experience, forgets what doesn't matter, and develops consistent personality. Add one URL. That's it.
Real workflows where persistent memory changes how AI works with you.
Claude remembers what broke last time. When reviewing similar code, it recalls past issues — "this auth pattern caused SSO failures" — and flags them proactively.
Your research assistant builds expertise over weeks. It remembers which papers you found useful, which approaches failed, and which leads to follow up.
After every deployment, reinforce what worked and what didn't. Claude develops institutional knowledge about your specific infrastructure quirks.
Everything runs compiled Rust via WASM on Cloudflare's edge. No cold starts. Sub-millisecond.
Memory that behaves like a brain, not a database.
Not everything gets remembered. Six factors — drive intensity, binding strength, co-activation, novelty, feedback, emotion — score each pattern. Below threshold? Silently rejected. Memory stays lean without manual curation.
Memories fade on cognitive science curves. Strong patterns decay slowly. Weak patterns get pruned. Reinforced patterns strengthen. The system self-maintains over months of continuous use without intervention.
Curiosity, creation, truth, protection, connection, autonomy, mastery, coherence. HASR oscillation modulates them over time. Your agent develops consistent character — not random personality shifts between sessions.