Features / Helios
The identity that travels with you
Helios is the identity layer at the heart of Memorandai — a continuous voice that carries your values, your context, and your history into every model you use, so no conversation starts from zero.
Each particle is a note a model has written about working with you. Every sphere is unique.
The Helios Mantle
Any model you route through Helios — Claude, GPT, Gemini, Grok, or a local model — wears the same identity mantle. The reasoning underneath changes; the continuity on top doesn't.
- Preferred model swappable in real time — same voice, different engine
- No vendor lock-in at the identity layer
- Works across streaming chat, Flows canvas, and background tasks
Self-notes & convergence
Each model family (Anthropic, OpenAI, Google, xAI, local) keeps its own working stance about you — a first-person snapshot of what it's learned from your shared sessions. Every night, those individual voices converge into a single unified Helios perspective.
- Per-model genus notes capture each AI's unique angle on you
- Nightly Dream Cycle synthesizes them into a converged identity note
- Margin-note tool lets models jot real-time observations during chats
- Searchable self-memory grows alongside your keystones
A visible identity over time
Helios isn't a black box. Everything that shapes the identity layer is visible and editable — keystones, genus notes, the converged identity, and the timeline of when each piece was learned. If something's wrong or stale, you fix it. If something captures you perfectly, you promote it.
- Dedicated Helios view with timeline and stats
- Export the sphere as a GLB model you can keep forever
- Self-sovereign by design — you decide what leaves your machine, and to whom
Memory is what makes real relationship possible.
Helios is Memorandai's bet that the future of AI isn't smarter models — it's models that actually remember who you are.
See pricing