Solving catastrophic forgetting with Recursive Time architecture, Active Sleep (generative replay), and Temporal LoRA. Proving the "Lazarus Effect" in neural networks.

Semantic knowledge graph engine with Raft consensus, HNSW vector search, neural memory (Ineru), zero-knowledge proofs, and P2P gossip sync. Powers the Cortex sidecar for AI agent frameworks.

Adaptive AI Agent Memory — Self-hosted MCP server that gets smarter as you use it. Hybrid search, neural memory graph, AI reranking, and web UI. Built with FastAPI, Next.js, PostgreSQL, and Qdrant.

Complete PyTorch reproduction of Google's TITANS, MIRAS, and NL neural memory papers. 52 tests, 87% coverage, Docker support.

事件驱动的多模态机器人操作系统 | 82K+ lines Python | 消费级硬件 | 一个设计师用AI搓出来的

Symbiogenesis is a memory-powered AI interface that evolves with you — combining neural recall (Mnemosyne) and predictive interaction (Prometheus) to enable true consciousness partnership.

Titans in PyTorch: Infinite Context models that learn to remember. Faster than Transformers, smarter than RNNs, and fully HuggingFace compatible.

A brain-inspired cognitive architecture exploring surprise-gated memory, identity protection, and the Titans/MIRAS framework.

Advanced neural networks with external memory systems for long-term reasoning and knowledge retention.

High-performance CUDA implementation of Titans neural memory architecture (Learning to Memorize at Test Time)

K-Slot Non-Merging Memory with Dual Writers (KNMM-DW) — long-context test-time-learning Transformer with falsifiable mechanism probes (polyphony / externality / unfinalizability).