A reproducible benchmark for learning and extending controlled symbolic sequences.
-
Updated
Oct 3, 2026 - Python
A reproducible benchmark for learning and extending controlled symbolic sequences.
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.
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.
Complete PyTorch reproduction of Google's TITANS, MIRAS, and NL neural memory papers. 52 tests, 87% coverage, Docker support.
The verifiable memory cortex for AI agents: a semantic graph and vector search with zero-knowledge provenance.
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.
Zero-decay neural memory V3.1 with instinct-level recall. Auto-remember 7 trigger types. 3-layer lazy recall. 46 MCP tools. Fact supersession. Schema v21. Neurons never die.
Zero-Decay Neural Memory for OpenClaw: decay_rate=0.0, neurons never pruned. Conflict resolution by certainty score. Auto-remember every decision. SimHash dedup. 4000-token budget.
Recurrent 64-slot KV-cache memory for Qwen3: PyTorch/Hugging Face training, x4 H100 evaluation, and honest tool-agent transfer diagnostics.
Advanced neural networks with external memory systems for long-term reasoning and knowledge retention.
Infinity Neural Memory V1 Final — append-only timeline, hybrid BM25+vector recall, governance gates, PII+secret redaction, Vietnamese NLP, 73 tests, zero deps. The honest memory brain for AI agents.
Next-generation agent architecture: recursive self-evolution, Titans neural test-time memory, and active inference OS world models.
High-performance CUDA implementation of Titans neural memory architecture (Learning to Memorize at Test Time)
Experiments with Titans Memory-as-Context and associative neural memory
Titans-style neural long-term memory for Qwen transformers
To associate your repository with the neural-memory topic, visit your repo's landing page and select "manage topics."