Qdrant
Qdrant is a vector similarity engine & vector database. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
Provides the OpenAPI v3 specification to generate a client library in almost any programming language. Alternatively utilise ready-made client for Python or other programming languages with additional functionality.
Implement a unique custom modification of the HNSW algorithm for Approximate Nearest Neighbor Search. Search with a State-of-the-Art speed and apply search filters without compromising on results.
Support additional payload associated with vectors. Not only stores payload but also allows filter results based on payload values.
Learn more
memU Bot
memU Bot is a proactive AI assistant that runs continuously on your device, learns your behavior and context, and offers personalized support rather than just reacting to commands; it adjusts tone, timing, and suggestions based on your mood, workload, and priorities while working 24/7 to anticipate and act on your needs. It is designed to be easy to start; you download and run it with no complex setup, and it stores long-term memory so it can recall preferences, habits, and history over time, making interactions more relevant and tailored to you. Unlike many reactive AI tools, memU Bot observes your workflows, remembers context across sessions, and can take proactive action based on predicted intent, helping with tasks before you explicitly request them. It emphasizes privacy and efficiency by running locally on your machine, keeping your data on your device without requiring uploads to third-party servers, which also helps reduce language model token costs.
Learn more
Papr
Papr is an AI-native memory and context intelligence platform that provides a predictive memory layer combining vector embeddings with a knowledge graph through a single API, enabling AI systems to store, connect, and retrieve context across conversations, documents, and structured data with high precision. It lets developers add production-ready memory to AI agents and apps with minimal code, maintaining context across interactions and powering assistants that remember user history and preferences. Papr supports ingestion of diverse data including chat, documents, PDFs, and tool data, automatically extracting entities and relationships to build a dynamic memory graph that improves retrieval accuracy and anticipates needs via predictive caching, delivering low latency and state-of-the-art retrieval performance. Papr’s hybrid architecture supports natural language search and GraphQL queries, secure multi-tenant access controls, and dual memory types for user personalization.
Learn more
EverMemOS
EverMemOS is a memory-operating system built to give AI agents continuous, long-term, context-rich memory so they can understand, reason, and evolve over time. It goes beyond traditional “stateless” AI; instead of forgetting past interactions, it uses layered memory extraction, structured knowledge organization, and adaptive retrieval mechanisms to build coherent narratives from scattered interactions, allowing the AI to draw on past conversations, user history, or stored knowledge dynamically. On the benchmark LoCoMo, EverMemOS achieved a reasoning accuracy of 92.3%, outperforming comparable memory-augmented systems. Through its core engine (EverMemModel), the platform supports parametric long-context understanding by leveraging the model’s KV cache, enabling training end-to-end rather than relying solely on retrieval-augmented generation.
Learn more