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.
agentscope-ai/agentscope
AgentScope is a comprehensive framework designed to facilitate the development of multi-agent applications empowered by large language models (LLMs). It emphasizes transparency, modularity, and customization, making it accessible for beginners while powerful enough for expert developers. The framework supports explicit message passing and workflow orchestration among multiple agents without deep encapsulation, allowing developers full control over prompt engineering, API invocation, agent building, and workflow management. Key features include real-time steering where agents can be interrupted and customized at any time, model-agnostic programming that allows running the same code with different models, and a LEGO-style modular approach to building agents. AgentScope supports asynchronous execution, parallel tool calls, and automatic state management, enhancing efficiency and scalability. It also offers agent-controlled long-term memory and hooks for extending agent capabilities. The framework includes a variety of modules such as model support for asynchronous invocation and streaming/non-streaming returns, tool management with synchronous and asynchronous functions, and multi-channel protocol (MCP) support for streamable HTTP/SSE/StdIO transport. It also provides tracing capabilities that integrate with third-party platforms, session and application-level state management, distributed and parallel evaluation, and multi-agent prompt formatting. AgentScope is developer-friendly with low-code development options, visual tracing, and monitoring tools, enabling a seamless transition from development to deployment. The project is well-documented with tutorials, FAQs, and a roadmap, and it is licensed under Apache 2.0. It supports Python 3.10+ and is actively maintained with recent updates and new tutorials. Overall, AgentScope is a robust and flexible platform for building sophisticated LLM-based multi-agent systems, promoting transparency, customization, and ease of use.
https://github.com/agentscope-ai/agentscope
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.
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.
gastownhall/beads
Beads is a distributed graph issue tracker for AI agents, powered by Dolt, providing a persistent, structured memory to manage long-horizon tasks without losing context.