neural-memory

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

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

Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any MCP client.

The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.

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

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.

Recurrent 64-slot KV-cache memory for Qwen3: PyTorch/Hugging Face training, x4 H100 evaluation, and honest tool-agent transfer diagnostics.

Experiments with Titans Memory-as-Context and associative neural memory

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

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

Titans-style neural long-term memory for Qwen transformers