nemori
A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.
Discover how Nemori handles LLM generation failures with a multi-layered fallback system. Ensure your AI memory pipeline remains resilient even with language model issues.
Nemori Prompt Templates: A Complete Guide to LLM InteractionsExplore Nemori prompt templates for effective LLM interactions. Discover eight core constants and helper methods for dynamic content formatting in a centralized class.
Where Are Nemori Memories Stored? Default Filesystem Organization ExplainedDiscover where Nemori memories are stored by default. Learn about the filesystem organization in the `./memories` directory, including episodic and semantic memory storage.
How to Configure Nemori for Different LLM Providers and Embedding ModelsConfigure Nemori for various LLM and embedding providers. Easily switch models, override URLs, or inject custom clients for flexible integration.
Nemori Evaluation Benchmarks: LoCoMo and LongMemEval ExplainedDiscover Nemori's evaluation benchmarks, LoCoMo and LongMemEval. Learn how they measure retrieval accuracy and LLM alignment for long-context reasoning.
How Nemori Ensures Semantic Coherence in Generated Episodes: A Technical Deep DiveExplore how Nemori ensures semantic coherence in generated episodes. Learn about its multi-stage pipeline including topic segmentation, LLM validation, and vector search.
How Nemori's Predict-Calibrate Learning Mechanism WorksUnderstand Nemori's predict-calibrate learning mechanism. Discover how Nemori continuously predicts and corrects conversations using semantic memories to extract novel knowledge and update its vector store.
How Nemori's Message Buffering and Segmentation Works: A Technical Deep DiveDiscover how Nemori's message buffering and segmentation works. Learn about thread-safe buffers and LLM-driven segmentation for efficient chat management.
Nemori Caching Strategies: How the AI Memory System Optimizes Performance with Four Thread-Safe LayersDiscover Nemori's four thread-safe caching strategies: per-user TTL, semantic-embedding, sharded LRU, and episode-storage. Optimize AI memory performance by reducing redundant computations and I/O.
How Nemori Handles Concurrent User Operations: Architecture and ImplementationDiscover how Nemori tackles concurrent user operations with per-user RLock, ThreadPoolExecutors, and sharded caching for high-throughput, race-free workloads. Learn its architecture and implementation.
Nemori Repository Architecture: 10 Key Files for Understanding the CodebaseUnderstand the Nemori repository architecture by exploring its 10 key files. Discover how config, memory system, and API facade files define its modular design.
How to Initialize and Use the Nemori MemorySystem: Complete GuideLearn to initialize and use the Nemori MemorySystem with our complete guide. Instantiate NemoriMemory and use add_messages, flush, and search for effortless conversational memory management.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →