OpenHands/OpenHands
OpenHands is an AI-powered platform that automates software development tasks, enabling developers to code less and produce more by modifying code, running commands, browsing the web, and integrating APIs efficiently.
NevaMind-AI/memU
MemU is an open-source memory framework designed specifically for AI companions, offering high accuracy, fast retrieval, and low operational costs. It functions as an intelligent memory folder that adapts to various AI companion scenarios, enabling AI systems to remember user interactions, preferences, and important information over time. MemU achieves a 92% accuracy rate on the Locomo benchmark, significantly outperforming competitors, and offers up to 90% cost reduction through optimized online platform usage. The framework supports advanced retrieval strategies including semantic search, hybrid search, and contextual retrieval, ensuring efficient and relevant memory recall. MemU provides three main deployment options: a cloud version for quick integration and managed infrastructure, an enterprise edition with enhanced security, customization, and analytics, and a self-hosting community edition for users prioritizing data privacy and control. The cloud version allows developers to integrate AI memory capabilities rapidly via API keys and simple code additions, while the enterprise edition offers commercial licenses, custom development, and 24/7 premium support. The framework organizes memories like a file system, autonomously managing memory folders through a memory agent that decides what to record, modify, or archive. It builds an interconnected knowledge graph linking related memories, transforming memory discovery into effortless recall. The system continuously evolves by generating new insights and summaries through self-reflection, even offline. An adaptive forgetting mechanism prioritizes frequently accessed memories and deprioritizes less relevant information, creating a personalized and dynamic memory hierarchy. MemU is ideal for AI companions, role-playing AI, AI characters, education, therapy, and robotics, among other applications. It emphasizes higher memory accuracy, fast retrieval by categorizing information into documents, and cost efficiency by processing multiple conversation turns simultaneously. The project is supported by a vibrant community, detailed documentation, and active development, making it a robust solution for persistent AI memory needs.
https://github.com/NevaMind-AI/memU
Also in AI Agents
usestrix/strix
Strix is an open-source AI-driven security testing platform that autonomously finds, validates, and helps fix application vulnerabilities through dynamic and collaborative AI agents.
aaif-goose/goose
Goose is an open-source, native AI agent available as a desktop app, CLI, and API, designed for diverse tasks like code, research, writing, and automation, supporting over 15 LLM providers.
KeygraphHQ/shannon
Shannon is an autonomous AI pentester for web applications and APIs, analyzing source code, identifying attack vectors, and executing real exploits to prove vulnerabilities.
wshobson/agents
A comprehensive collection of 44 specialized AI subagents for Claude Code that enhance development workflows with domain-specific expertise across software development, infrastructure, security, data, and business domains.
agentscope-ai/agentscope
AgentScope is a transparent, modular, and customizable framework for building LLM-empowered multi-agent applications with real-time control and asynchronous execution.
iOfficeAI/OfficeCLI
OfficeCLI is an open-source command-line interface and API enabling AI agents to read, edit, and automate Word, Excel, and PowerPoint files without needing Office suite installations.
langchain-ai/deepagents
Deep Agents is an open-source agent harness built on LangChain and LangGraph that enables AI agents to plan, execute, and delegate complex long-horizon tasks using customizable tools, subagents, and human-in-the-loop workflows.