Awesome GitHub RepositoriesKnowledge and Memory

The Model Context Protocol is a standardized communication framework designed to connect language models to external data sources, functional tools, and interactive user interfaces. It provides a vendor-neutral interface layer that enables AI hosts to discover and execute capabilities across heterogeneous service environments, using a JSON-RPC based messaging standard to facilitate bidirectional communication between clients and servers. The protocol distinguishes itself through a robust capability-based handshake that negotiates feature sets during session initialization, ensuring compatibil

Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model interactions. It functions as an intermediary that intercepts traffic between clients and providers to apply context compression, request routing, and format translation. The system differentiates itself through a Model Context Protocol server implementation that delivers compression and retrieval tools to compatible AI hosts. It employs a content-aware compression pipeline and tiered importance scoring to trim redundant data from logs and tool outputs while preserving essential

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

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

OpenMetadata is an enterprise data catalog, metadata platform, and governance suite that functions as a knowledge graph for data assets. It serves as an AI-ready metadata layer, providing governed context and organizational memory to large language model agents via the Model Context Protocol. The platform distinguishes itself by capturing institutional knowledge, linking conversations, decisions, and remediation notes directly to data assets to preserve tribal knowledge. It integrates AI agents to automate metadata governance, such as suggesting descriptions and identifying sensitive data thr

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

an ambient intelligence library

This project is an AI assistant integration that connects OpenAI models to the Feishu team communication platform. It functions as a multi-model gateway that routes requests to GPT-4, GPT-4V, DALL-E-3, and Whisper models, enabling voice conversations, image generation, and multi-topic dialogues within team chats. The assistant operates through a bridge layer that translates Feishu chat events into internal commands, supporting plugin-based persona switching to alter response behavior and tone for different use cases. It distributes API requests across multiple authentication tokens for load b

This project is a ChatGPT-powered bot integrated into the Feishu chat platform, enabling conversational AI, image generation, and voice interaction within both private and group chats. It connects large language models to the team messaging environment, allowing users to engage in multi-topic conversations, generate images from text prompts, and analyze uploaded images using vision models. The bot supports persona preset switching, allowing predefined role templates to modify the AI's behavior and tone with a single command. It maintains separate conversation histories per topic using session

MemOS is an open-source persistent memory layer for AI agents and large language models, providing a self-hosted server that stores and retrieves structured memory across sessions. It enables AI systems to recall user preferences, history, and context without retraining, using a graph-based API and a web management interface for viewing, editing, and organizing memory items, skills, traces, and knowledge bases. The system distinguishes itself through a portable memory interchange protocol that allows memory to be transferred between different AI models, devices, and applications, along with a

Open Canvas ist ein System zur Verwaltung zustandsbehafteter KI-Agenten-Workflows durch einen kollaborativen Editor und ein Orchestrierungs-Framework. Es bietet einen gemeinsamen Arbeitsbereich, in dem Menschen und Large Language Models in Echtzeit Dokumente verfassen und Code schreiben, unterstützt durch einen strukturierten Texteditor mit Live-Rendering. Das Projekt zeichnet sich durch die Integration eines Status-Managers aus, der Sitzungskontext, Benutzererinnerungen und historische Snapshots über Konversations-Threads hinweg verfolgt. Es verwendet ein dauerhaftes Ausführungsmodell, das menschliche Eingriffe ermöglicht und ein Versionsverfolgungssystem für Dokumente und Code-Blöcke unterhält. Das Framework deckt ein breites Funktionsspektrum ab, einschließlich Provider-agnostischer Modellschnittstellen für Chat und Embeddings, Middleware-gesteuerter Workflow-Komposition für Guardrails und Routing sowie persönlichem Kontextmanagement zur Speicherung von Benutzerpräferenzen. Es enthält zudem Tools für das Debugging von Agentenausführungen und die Möglichkeit, den Server mittels Container-Images bereitzustellen. Ein lokaler Agenten-Server wird bereitgestellt, um Läufe, Threads und persistente Speicherung zu handhaben.

Dieses Projekt ist ein Wissensdatenbank-Plugin und RAG-Kontextmanager, der eine lokale Vektordatenbank-Schnittstelle nutzt, um semantische Suche und Beziehungsmapping zu ermöglichen. Es transformiert Text in numerische Vektoren, um semantisch verwandte Notizen und Auszüge basierend auf konzeptioneller Bedeutung statt nur nach Schlüsselwortübereinstimmungen zu finden. Das System zeichnet sich durch einen semantischen Graph-Visualisierer aus, der Notizen in Clustern abbildet, um konzeptionelle Verbindungen aufzudecken. Es verfügt zudem über einen Kontextmanager, der lokale Notizen und Auszüge in wiederverwendbare Pakete bündeln kann, um fundierte Faktenbasen für Konversationen mit großen Sprachmodellen bereitzustellen. Das Tool deckt eine breite Palette an Funktionen ab, darunter die Abfrage von natürlichsprachlichem Wissen, die automatisierte Workflow-Ausführung für die Notizerstellung und die Möglichkeit, Prompts zwischen lokalen und Cloud-basierten KI-Modellen zu routen. Es bietet verschiedene Discovery-Schnittstellen, wie z. B. Inline-Indikatoren für verwandte Inhalte und ein Fußzeilen-Panel zum Einblenden ähnlicher Dokumente während des Bearbeitungsprozesses.

PromptX is an LLM agent orchestration framework designed to execute multi-step workflows using autonomous agents. It features a sandboxed tool execution environment for secure filesystem operations and external API integrations, alongside a persona management system that defines professional roles and domain expertise to control agent behavior. The system implements a semantic memory network for persistent knowledge storage, utilizing graph-based memory and engrams to retain information across sessions. This cognitive memory includes specialized tools for knowledge graph visualization, allowi

On-premises conversational RAG with configurable containers

mem0-mcp-server wraps the official Mem0 Memory API as a Model Context Protocol (MCP) server so any MCP-compatible client (Claude Desktop, Cursor, custom agents) can add, search, update, and delete long-term memories.

Model Context Protocol (MCP) Server for Graphlit Platform

A knowledge graph server that uses the Model Context Protocol (MCP) to provide structured memory persistence for AI models.

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.