MemoraCore live on @base basescan.org/token/0xc117070…

Memora Startup on @BetaList betalist.com/startups/memora…

Memora enables you to create your own personalized AI system. with Memora, allowing your AI to do more than just respond—it learns, adapts, and evolvesalongside you.

Our GitHub github.com/ELZAI/memora/

Synapse: Your Personal AI is Live Synapse enables you to create your own personalized AI system. with Memora, allowing your AI to do more than just respond—it learns, adapts, and evolvesalongside you. elzai.com

More info about Synapse AI elzai.com

Conversations with Personal AI (eg Character AI) should not have - delete - regenerate response - start new thread Humans don't interact like that

Emotion-Tagged Memories: Allowing AI to recall memories along with the emotions experienced at that time, such as joy 😄, sadness 😢, surprise 😲.

Currently, Memora manages text-based memories, assisting AI in maintaining context and evolving over time. However, our dream is way bigger towards the full spectrum of human memory, enabling AI to interact as naturally as a close friend.

Prompts. System prompts and input templates used by the LLM in various memory operations.

Schemas. Pydantic data models that are used for structured memory extraction, storage, and retrieval to ensure consistency and model structured output.

LLM Backends An interface for LLM providers, along with some implementations, that Memora can use in the backend for memory operations, such as understanding context, determining what to store and recall, linking memories to source messages and more.

Vector Database Enables semantic search across memories using dense vector embeddings for semantic similarity, combined with sparse text embeddings (like SPLADE) for hybrid search.

Graph Database Currently, our graph database implementation focuses on storing organizations, agents, users, their interactions with the agent (messages), and the memories derived from these interactions, all with date and time etc.