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.
langchain-ai/deepagents
Deep Agents is an open-source agent harness built on top of LangChain and LangGraph frameworks, designed to empower AI agents to handle complex, long-horizon tasks that require multiple steps and tool interactions. The project addresses challenges related to cost and reliability in executing extended sequences of tool calls by incorporating key principles such as planning before task execution, access to a computer shell and filesystem, and delegation of tasks to sub-agents for isolated execution. This architecture allows Deep Agents to manage sophisticated workflows by breaking down tasks into manageable components and leveraging specialized sub-agents. The project provides a flexible and extensible platform where users can customize agents with their own tools, system prompts, and models. It supports integration with external APIs, such as web search tools, and allows for the creation of domain-specific workflows through custom system prompts. Deep Agents also supports human-in-the-loop workflows, enabling human approval for sensitive tool executions, enhancing control and safety. Deep Agents uses middleware for extensibility, allowing injection of custom tools and modification of agent behavior. It supports pluggable backends for filesystem operations, enabling different storage strategies including ephemeral, local disk, or persistent storage. The agents are compiled into LangGraph StateGraph format, making them compatible with streaming, memory, and interactive workflows. The project includes comprehensive documentation, quickstart examples, and a command-line interface for interactive use. It is designed to be open and easily extendable, encouraging users to build upon its capabilities for research, data analysis, and other complex AI-driven tasks. Overall, Deep Agents provides a robust framework for developing intelligent agents capable of sophisticated task planning, execution, and delegation in a modular and customizable manner.
https://github.com/langchain-ai/deepagents
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.
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.