awesome-repositories.com
Blog
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoAcerca deCómo clasificamosPrensaServidor MCP
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
supermemoryai avatar

supermemoryai/supermemory

0
View on GitHub↗
27,334 estrellas·2,378 forks·TypeScript·MIT·8 vistassupermemory.ai↗

Supermemory

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 search with structured graph traversal to retrieve both semantic context and explicit relational data. It decomposes unstructured documents into granular, standalone facts and utilizes composable retrieval pipelines to refine information before it is injected into agent prompts. This architecture supports the creation of automated user profiles and fact hierarchies, allowing the system to learn and update information in real-time while managing the lifecycle of stored data.

Beyond individual agent support, the platform facilitates enterprise knowledge sharing by maintaining collective repositories of project decisions and patterns. It automates data ingestion from diverse sources, including cloud storage, productivity platforms, and web content, using event-driven synchronization to ensure information freshness. The platform is designed for self-hosted, containerized deployment, providing users with full control over their data infrastructure and sovereignty.

Features

  • Agent Memory Stores - Provides autonomous agents with persistent, long-term knowledge bases to maintain context across complex workflows.
  • Agent Memory Maintenance - Provides persistent knowledge bases for autonomous coding assistants to maintain long-term context across multi-session workflows.
  • AI Knowledge Management - Acts as a centralized knowledge base that synchronizes multimodal data to provide persistent context for AI agents.
  • Self-Hosted AI Infrastructure - Provides a private deployment solution for managing long-term memory and document synchronization.
  • Self-Hosted Deployment Platforms - Supports private, self-hosted deployment to ensure full control over data infrastructure and sovereignty.

Búsqueda con IA

Explora más repositorios increíbles

Describe lo que necesitas en lenguaje sencillo: la IA clasifica miles de proyectos open-source curados por relevancia.

Start searching with AI
  • Hybrid Search Engines - Integrates vector similarity, keyword matching, and graph traversal for high-precision information retrieval.
  • Hybrid Vector-Graph Databases - Combines vector similarity search with structured graph traversal to retrieve both semantic context and explicit relational data.
  • Knowledge Graph Construction Tools - Constructs semantic relationships between data points to enable complex retrieval across historical project context.
  • Vector Database Orchestrators - Orchestrates the indexing, retrieval, and re-ranking of structured facts to improve AI response relevance.
  • Agent Memory Storage - Provides persistent storage for agent memory by linking semantic facts and historical context across sessions.
  • Context Injection - Automatically inserts relevant historical data into active prompts to maintain continuity across long-term tasks and multi-session workflows.
  • Knowledge Graph Construction - Constructs automated user profiles and fact hierarchies to allow agents to learn and update information in real-time.
  • Memory Retrieval Systems - Queries the database to find specific documents and facts based on user-defined criteria.
  • Retrieval Pipelines - Applies sequential operations like query rewriting, filtering, and result re-ranking to refine data before it reaches the agent.
  • Knowledge Management - Maintains collective repositories of project decisions and patterns to facilitate enterprise knowledge sharing.
  • AI-Integrated Knowledge Bases - Connects AI tools to a shared knowledge base for cross-session context recall and information persistence.
  • Graph Traversal Strategies - Navigates relationships between linked data points to retrieve contextual information across the knowledge base.
  • Multimodal Data Extractors - Extracts and structures multimodal content into semantically linked facts for automated retrieval.
  • Query Optimization - Refines and enriches retrieved data using re-ranking and query rewriting operations.
  • Memory Management - Scalable memory engine and application.
  • Data Ingestion - Automates the extraction and processing of diverse media formats into structured data for AI consumption.
  • Document and Unstructured Extraction - Parses unstructured text into individual, standalone data points to ensure information is stored in a granular, searchable format.
  • External Data Integrations - Synchronizes documents from third-party cloud storage and productivity platforms into a centralized repository for automated processing.
  • Semantic Memory Generation - Decomposes documents into semantically meaningful chunks and resolves references to create high-signal, fact-based memory entries.
  • Semantic Chunking - Processes diverse media formats into semantically meaningful segments to enable unified retrieval across text, images, and audio.
  • Personal Knowledge Management - Centralizes information from diverse sources into a single searchable repository for personal knowledge management.
  • Team Collaboration Platforms - Maintains a collective repository of project decisions and patterns to accelerate team onboarding and historical context access.
  • Document Decomposition - Breaks unstructured documents into granular, standalone data points to improve the precision and relevance of information retrieval.
  • Data Integration & Synchronization - Synchronizes stored information across multiple integrated platforms and tools to ensure context remains accessible.
  • Data Lifecycle Management - Expires temporary information based on time or significance and resolves contradictory data to maintain an accurate knowledge base.
  • Event-Driven - Uses webhooks and scheduled polling to maintain a synchronized knowledge base by automatically capturing updates from external sources.
  • Document Storage - Centralizes text-based documents and information into a database for efficient management and retrieval.
  • Automated Update Managers - Maintains data freshness through real-time webhooks and scheduled polling of external sources without manual intervention.
  • Event Capture - Saves conversations, decisions, and project information into storage with a single command to preserve important details.
  • Workspace Organization - Segments stored information into isolated workspaces to maintain separate knowledge bases for different initiatives.
  • Web Crawling - Systematically discovers and indexes public web content to capture information for retrieval.

    • Historial de estrellas

    Gráfico del historial de estrellas de supermemoryai/supermemoryGráfico del historial de estrellas de supermemoryai/supermemory

    Preguntas frecuentes

    ¿Qué hace supermemoryai/supermemory?

    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…

    ¿Cuáles son las características principales de supermemoryai/supermemory?

    Las características principales de supermemoryai/supermemory son: Agent Memory Stores, Agent Memory Maintenance, AI Knowledge Management, Self-Hosted AI Infrastructure, Self-Hosted Deployment Platforms, Hybrid Search Engines, Hybrid Vector-Graph Databases, Knowledge Graph Construction Tools.

    ¿Qué alternativas de código abierto existen para supermemoryai/supermemory?

    Las alternativas de código abierto para supermemoryai/supermemory incluyen: falkordb/falkordb — FalkorDB is a high-performance graph database management system and vector graph database. It serves as a knowledge… topoteretes/cognee — Cognee is an agentic memory management platform designed to provide autonomous agents with long-term semantic recall… arangodb/arangodb — This project is a multi-model database system designed to store and manage information as documents, graphs, and… camel-ai/camel — This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified… tinyhumansai/openhuman — OpenHuman is an AI application framework for building private intelligence systems and personal AI layers. It provides… memorilabs/memori — Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language…

    Alternativas open-source a Supermemory

    Proyectos open-source similares, clasificados según cuántas características comparten con Supermemory.
    • falkordb/falkordbAvatar de FalkorDB

      FalkorDB/FalkorDB

      3,437Ver en GitHub↗

      FalkorDB is a high-performance graph database management system and vector graph database. It serves as a knowledge graph construction tool and a GraphRAG knowledge store, integrating structured property graphs with vector search to provide grounded context for large language models. The engine is designed as a multi-tenant graph engine, capable of hosting thousands of isolated datasets within a single instance. The system distinguishes itself by using linear algebra for query execution, treating relationship tensors as matrix multiplications to achieve low-latency multi-hop traversals. It ut

      Ccloud-databasedatabasedatabase-as-a-service
      Ver en GitHub↗3,437
    • topoteretes/cogneeAvatar de topoteretes

      topoteretes/cognee

      17,850Ver en GitHub↗

      Cognee is an agentic memory management platform designed to provide autonomous agents with long-term semantic recall and structured knowledge. It functions as a framework for building persistent memory systems that connect large language models to graph-based knowledge and vector storage, enabling agents to maintain context across complex tasks and multiple sessions. The platform distinguishes itself through a hybrid approach that combines semantic similarity search with structural graph traversal, allowing for context-aware information retrieval. It features a modular architecture that orche

      Pythonaiai-agentsai-memory
      Ver en GitHub↗17,850
  • arangodb/arangodbAvatar de arangodb

    arangodb/arangodb

    14,091Ver en GitHub↗

    This project is a multi-model database system designed to store and manage information as documents, graphs, and key-value pairs within a single engine. It functions as a graph database and knowledge graph platform, providing the infrastructure to build, query, and visualize structured data models. By integrating vector search capabilities, the system serves as a vector database that supports retrieval-augmented generation for artificial intelligence applications. The platform distinguishes itself through a unified query language that allows users to perform document lookups, graph traversals

    C++arangodbdatabasedistributed-database
    Ver en GitHub↗14,091
  • camel-ai/camelAvatar de camel-ai

    camel-ai/camel

    17,253Ver en GitHub↗

    This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

    Pythonagentai-societiesartificial-intelligence
    Ver en GitHub↗17,253
    • Ver las 30 alternativas a Supermemory→