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.
AgentFS is a specialized filesystem designed specifically for AI agents, providing essential storage abstractions tailored to their needs. Unlike traditional filesystems that serve general applications, AgentFS focuses on managing the state, files, and tool interactions of AI agents in a structured and auditable manner. The project includes SDKs in TypeScript, Python, and Rust, enabling programmatic access to the filesystem, as well as a command-line interface (CLI) for managing agent filesystems. The CLI supports mounting AgentFS on host systems using FUSE on Linux and NFS on macOS, allowing seamless file operations and inspection. At its core, AgentFS uses a SQLite-based storage system to maintain a comprehensive record of every file operation, tool call, and state change performed by an agent. This design offers several key benefits: auditability, reproducibility, and portability. Auditability is achieved by recording all actions in a SQLite database, enabling users to query the agent's history for debugging, behavior analysis, or compliance. Reproducibility allows users to snapshot and restore an agent's state at any point, facilitating testing and rollback of changes. Portability is ensured by encapsulating the entire agent runtime—including files, state, and history—within a single SQLite file that can be easily moved, version-controlled, or deployed. AgentFS also provides a key-value store interface and a toolcall audit trail, enhancing the management of agent state and context. The project includes examples demonstrating integration with popular AI frameworks such as Mastra, Anthropic's Claude Agent SDK, OpenAI Agents SDK, and others. This makes AgentFS a versatile tool for developers building AI agents that require persistent, queryable, and portable state management. Overall, AgentFS addresses the unique challenges of AI agent state management by combining filesystem abstractions with robust auditing and snapshot capabilities, making it a valuable resource for AI development and experimentation.
https://github.com/tursodatabase/agentfs
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.
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.
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.
Shannon is an autonomous AI pentester for web applications and APIs, analyzing source code, identifying attack vectors, and executing real exploits to prove vulnerabilities.
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 is a transparent, modular, and customizable framework for building LLM-empowered multi-agent applications with real-time control and asynchronous execution.
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.
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.