Awesome GitHub RepositoriesMemory-Optimized Storage

Supermemory is an artificial intelligence memory management platform designed to provide autonomous agents with persistent, long-term knowledge bases. It functions as a centralized repository that synchronizes multimodal data, enabling agents to maintain context and historical information across complex, multi-session workflows. By serving as a knowledge graph engine and vector database orchestrator, the platform ensures that information remains accessible and relevant for automated tasks. The system distinguishes itself through its hybrid indexing approach, which combines vector similarity s

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions. The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface rel

Vector similarity search extension for PostgreSQL.

TurboVec is a high-performance Rust vector database and quantized search index designed for storing and retrieving high-dimensional embeddings. It functions as a pluggable vector store for large language model orchestration frameworks, providing a memory-efficient alternative to standard in-memory storage. The project distinguishes itself through a high-dimensional vector compressor that utilizes random rotation and data-oblivious scalar quantization to reduce memory footprints. Retrieval is accelerated via SIMD kernels that process distance calculations and search operations for increased th

Redis is a high-performance in-memory key-value store that functions as a distributed cache, message broker, and NoSQL database. It provides sub-millisecond read and write access to data stored in RAM and can operate as a vector database for indexing high-dimensional embeddings. The system supports a wide range of data storage and synchronization primitives, including the management of strings, hashes, lists, sets, and JSON documents. It enables real-time data operations through atomic transactions, hybrid persistence using snapshots and append-only logs, and high-availability configurations

jcode est un framework pour développer des agents de codage IA autonomes qui automatisent les tâches de développement logiciel. Il fonctionne comme un orchestrateur d'agents, un runtime d'outils et un moteur de mémoire sémantique, permettant la création d'agents capables de modifier du code, d'exécuter des tests et d'itérer sur leur propre fonctionnalité. Le projet se distingue par son utilisation de l'essaimage d'agents récursif, où une hiérarchie d'agents collaborateurs peut engendrer des agents enfants pour décomposer des tâches complexes. Il implémente un système de mémoire sémantique qui combine la récupération basée sur des vecteurs avec le mappage de relations basé sur des graphes pour maintenir le contexte à travers les sessions. Pour gérer les risques, le système utilise une gouvernance d'action à plusieurs niveaux qui nécessite une approbation humaine pour les opérations sensibles et isole les activités des agents dans des worktrees git séparés. Le framework inclut une boîte à outils complète d'automatisation de navigateur pour interagir avec les pages web, extraire des snapshots DOM et capturer des captures d'écran. Il implémente également le Model Context Protocol pour intégrer des outils et des données externes, et prend en charge le rechargement à chaud binaire pour mettre à jour le serveur sans perdre les connexions réseau actives. Le système fournit une interface en ligne de commande pour gérer les mémoires des agents et inclut des outils d'audit pour suivre la progression du plan et visualiser la topologie de l'essaim d'agents.

sqlite-vec is a C-based vector library and SQLite extension that adds virtual tables for storing and querying high-dimensional embeddings. It functions as a database plugin for performing nearest neighbor searches using distance metrics such as L2, cosine, and Hamming distance. The project provides a portable embedding store that supports deployment across Android, iOS, desktop environments, and web browsers via WebAssembly. It distinguishes itself by converting numerical arrays into compact binary formats and utilizing quantization to reduce the memory footprint and storage size of vector in

AIOS is an LLM agent operating system and orchestration kernel designed to manage memory, resource scheduling, and tool execution for multiple autonomous AI agents. It serves as a comprehensive framework for developing and deploying agents, featuring a dedicated resource manager that coordinates model backends, GPU memory, and isolated kernel instances. The system distinguishes itself through a semantic memory engine that uses vector search and autonomous clustering for long-term knowledge management, and a semantic file system that allows users to control computer files and system operations

TinyPinyin est une bibliothèque compatible Java et Android utilisée pour convertir les caractères chinois en représentations phonétiques Pinyin. Elle fournit des utilitaires pour la détection de caractères chinois afin d'identifier si le texte appartient au système d'écriture chinois. La bibliothèque inclut un résolveur de caractères polyphoniques qui détermine la prononciation correcte pour les caractères ayant plusieurs sons via une analyse contextuelle. Elle est conçue pour une faible utilisation de la mémoire sur les appareils mobiles.

OpenMemory is an embeddable memory engine for LLM agents that stores, retrieves, and manages conversational context and agent state using semantic indexing and temporal facts. It functions as a semantic memory store backed by vector indexing, where memories are organized by meaning rather than by exact key, and includes a tiered decay engine that gradually reduces the salience of unused memories while compressing cold vectors and fingerprinting dormant entries to conserve storage. The system also maintains a temporal fact database that records factual statements with subject-predicate-object s

OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a

pgvecto.rs is a database extension that integrates high-dimensional vector search capabilities directly into PostgreSQL. It functions as a specialized engine for storing and retrieving embeddings, allowing relational databases to perform similarity searches alongside traditional structured data queries. The extension distinguishes itself through hardware-aware execution strategies that maximize performance. It performs runtime analysis of the host machine to utilize specific processor instruction sets for accelerated mathematical operations. To manage memory efficiently, it employs quantizati