Open-source alternatives to Trycua Cua

VirtualBuddy is a graphical user interface and manager for creating and running macOS virtual machines on Apple Silicon. It serves as an interface for the native Apple Virtualization Framework, allowing users to provision and boot guest operating systems on ARM-based hardware. The tool provides a dedicated environment for managing virtual machine administration and software compatibility testing across different macOS versions. It enables the execution of guests via local files, remote URLs, or image catalogs, and supports booting into recovery mode for system repairs. The system covers hard

Bytebot is an LLM desktop automation framework and virtual Linux desktop environment. It enables AI agents to plan and execute mouse and keyboard actions on a virtual computer using natural language, allowing for autonomous desktop automation and the integration of legacy systems that lack native APIs. The system operates as an LLM API gateway and a Model Context Protocol server, routing requests across multiple language model providers with integrated load balancing and rate limiting. It provides isolated, containerized environments where agents use visual reasoning to interpret screenshots

Open-computer-use is a framework designed to connect vision-capable language models to isolated cloud-based desktop environments. It functions as an agentic interface that enables autonomous systems to interact with graphical user interfaces by simulating mouse movements, keyboard keystrokes, and shell commands. By bridging language models with remote workspaces, the platform facilitates the execution of complex, long-running tasks within secure, sandboxed environments. The platform distinguishes itself through its ability to orchestrate thousands of concurrent, isolated instances, making it

Tart is an Apple Silicon virtualization manager used to build and run macOS and Linux virtual machines using native hardware virtualization frameworks. It functions as a virtual machine cluster orchestrator and an ephemeral runner for executing continuous integration pipeline steps within isolated, short-lived environments. The system utilizes an OCI-compatible virtual machine registry to push and pull images via standardized container registries. It features a controller-worker architecture that schedules virtual machine lifecycles across remote worker nodes, incorporating a secure SSH jump

microvm.nix is a declarative virtual machine manager and orchestrator for defining, building, and managing isolated guest environments using Nix. It functions as a virtual machine image builder that transforms system specifications into bootable disk images and runner scripts. The project provides a hypervisor abstraction layer, enabling the deployment of guest images across multiple virtualization backends through a unified configuration. It includes specialized tools for PCI hardware passthrough, granting virtual machines direct access to physical host USB and PCI devices. The framework co

LXD is a system container manager and virtual machine manager that provides a unified interface for running full Linux systems. It acts as a container cluster orchestrator, an image format converter, and an infrastructure manager that exposes control through a REST API and language-specific SDKs. The project distinguishes itself by providing a unified container and virtual machine abstraction, treating both as generic instances within a single management layer. It supports distributed cluster coordination to synchronize state and distribute workloads across multiple physical nodes. The syste

LXD is a unified platform for managing both system containers and virtual machines through a single REST API and command-line interface. It provides a programmatic HTTP interface for controlling the full lifecycle of instances, enabling automation and integration with external tools. The system runs unprivileged containers with per-instance UID/GID mappings, seccomp filters, and AppArmor profiles for kernel-level isolation, while supporting multiple storage backends including directory, Btrfs, LVM, ZFS, Ceph, LINSTOR, and TrueNAS through a unified driver interface. The platform distinguishes

Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin

OrbStack is a native macOS application that replaces Docker Desktop, providing an all-in-one environment for running Docker containers, full Linux virtual machines, and local Kubernetes clusters. It runs Linux VMs directly on the macOS hypervisor framework for near-native performance, uses VirtioFS for fast bidirectional file sharing between macOS and Linux, and leverages Rosetta for near-native x86 emulation on Apple Silicon. The system assigns predictable local domain names to containers and VMs with automatic HTTPS certificate generation, forwards ports via event-driven updates, and stores

Boto3 is the AWS SDK for Python, providing a programmatic interface for managing and automating AWS cloud infrastructure and services. It serves as a cloud management API client and resource manager for provisioning, configuring, and scaling virtual servers, databases, and storage. The library enables the implementation of infrastructure-as-code through declarative templates and scripts, allowing for the deployment of identical resource stacks across multiple accounts and geographic regions. It also provides a framework for coordinating distributed workflows, serverless functions, and contain

OmniParser is a multimodal interaction engine designed to function as a desktop automation agent. It interprets visual screen information to execute complex, multi-step tasks across operating system environments by bridging visual interface perception with language models. Through a continuous cycle of observation and command execution, the system grounds high-level natural language instructions into precise, coordinate-based actions. The project distinguishes itself by utilizing vision-based parsing to interact with software interfaces without requiring access to underlying application progr

Rikkahub is an AI model aggregator and frontend interface that provides a unified platform for interacting with multiple large language model providers. It serves as a retrieval-augmented generation chat client with a provider-agnostic gateway, allowing users to switch between different models and endpoints. The platform features a character persona manager for importing structured character cards and behavior settings to define specific interaction styles. It includes a sandboxed code execution environment with a portable Linux agent for running technical scripts and commands within the chat

Cockpit is a web-based management interface designed for the administration of Linux servers. It provides a graphical environment that allows users to perform system tasks, configure server settings, and monitor performance directly through a standard browser. The platform distinguishes itself by offering centralized control over distributed environments, enabling the management of multiple servers from a single dashboard. It supports the lifecycle management of containerized workloads and virtual machine infrastructure, alongside the configuration of network interfaces, firewalls, and storag

Vagrant is a virtual machine environment manager and development environment provisioner. It functions as an infrastructure as code tool and multi-hypervisor orchestrator, allowing for the definition and automation of virtualized development environments through a single configuration file. The project enables the creation of portable, virtualized development environments to ensure consistency across different host operating systems. It supports deploying these environments across various backends, including local hypervisors, cloud providers, and container runtimes, using a unified interface

This project is a comprehensive repository and curated index of resources, research papers, and development frameworks designed to support the construction and deployment of intelligent systems. It serves as a centralized knowledge base for developers seeking to navigate the technical landscape of artificial intelligence, ranging from foundational educational materials to specialized implementation guides. The repository distinguishes itself by providing structured directories for comparing generative artificial intelligence providers, including aggregated performance metrics, pricing data, a

This project is a comprehensive research platform designed for the end-to-end lifecycle of robotic learning. It provides a modular framework for training neural network policies—specifically through imitation and reinforcement learning—and deploying them onto physical robotic hardware. By offering a unified interface for hardware abstraction, the platform decouples high-level control logic from the specific sensors and actuators of diverse robotic systems. The framework distinguishes itself through a standardized approach to data and policy management. It utilizes a consistent schema for reco

Quickemu is a command-line utility designed to automate the deployment and management of virtual machine instances. It functions as an automated provisioner that handles the acquisition of operating system images and the generation of optimized configuration files, allowing users to launch virtualized environments with minimal manual setup. The tool leverages hardware-accelerated emulation to execute virtual machines, mapping host-native resources directly to the guest environment to maintain performance. It utilizes shell-scripted orchestration to manage the lifecycle of these instances, sto

UI-TARS-desktop is a cross-platform desktop application designed to automate software interface interactions. It functions as a local agent environment that interprets graphical user interfaces through multimodal visual-language model reasoning, allowing it to navigate and manipulate software by simulating human-like mouse and keyboard inputs. The platform distinguishes itself by executing all visual recognition and decision-making logic directly on the host machine. This local inference model ensures that screen data and sensitive information remain private, as no processing is offloaded to

WinApps is a utility designed to run Windows applications within a virtualized environment while integrating them directly into a Linux desktop. By utilizing remote desktop protocols to stream graphical interfaces, the software allows virtualized programs to appear and behave as if they were installed natively on the host operating system. The project distinguishes itself by automating the discovery and configuration of these applications. It scans the guest registry to identify installed software and automatically generates desktop entries and shortcuts, enabling users to launch Windows prog

This project provides a containerized environment for running a full macOS desktop operating system. It utilizes a hardware-accelerated virtualization engine to execute the guest environment, allowing for the deployment and management of virtual machines through standard container orchestration tools. The platform distinguishes itself by enabling direct hardware passthrough, which maps physical host disks, partitions, and USB controllers directly into the virtual machine for native driver access. It also supports advanced network integration, allowing the guest system to obtain its own unique

Daytona is a cloud-native development environment platform designed to orchestrate ephemeral, containerized workspaces. It provides a centralized system for managing reproducible coding environments as code, ensuring consistency across distributed teams by abstracting the underlying infrastructure. By utilizing declarative configuration, the platform automates the entire lifecycle of development sandboxes, from initial provisioning to resource governance. The platform distinguishes itself through its infrastructure-agnostic runner layer, which allows development environments to be deployed ac

Chalice is a framework for building and deploying serverless applications and REST APIs on AWS Lambda using Python. It functions as an infrastructure-as-code generator, mapping application logic and routing definitions directly to cloud compute resources while automating the provisioning and management of the underlying environment. The framework distinguishes itself by analyzing source code to automatically construct the minimum necessary security permissions, ensuring least-privilege access for all deployed functions. It supports modular development through blueprint-based organization and

virt-manager is a graphical management interface for configuring hypervisors, virtual machine instances, and containers via the libvirt API. It provides a desktop environment for managing KVM-based virtualization on Linux hosts, acting as a centralized controller for both local and remote hypervisors. The project distinguishes itself through integrated management of the surrounding virtualization infrastructure. It includes dedicated interfaces for virtual network administration to connect guests to physical hardware and virtual storage management for organizing disk volumes into logical pool

Screenpipe is a local-first platform designed to record, index, and analyze desktop activity. By capturing screen, audio, and keyboard input, it creates a comprehensive and searchable history of computer usage. The system functions as an activity recorder and automation framework, providing a persistent, context-aware memory that allows artificial intelligence agents to observe and interact with local desktop environments. The platform distinguishes itself through a privacy-focused architecture that processes all data locally. It utilizes on-device computer vision and speech recognition to tr

Colima is a command-line utility that provides lightweight container runtimes and local Kubernetes orchestration by managing isolated virtual machine environments. It functions as a virtualization manager that abstracts the underlying container engine, allowing users to run containerized applications and system workloads on non-native operating systems without the overhead of heavy desktop software. The project distinguishes itself through its support for hardware-accelerated workloads, enabling direct GPU passthrough to virtual machines for high-performance machine learning tasks. It offers

Openwork is an AI agent for desktop automation that uses large language models to execute browser tasks, manage local files, and automate desktop workflows. It operates on a local-first execution model, translating natural language prompts into sequences of tool calls to perform digital chores. The system functions as a framework for defining and saving repeatable sequences of actions as reusable skills. It integrates large language models with third-party services and local APIs to synchronize data and share files. The agent includes capabilities for headless browser automation to conduct r

Kit is a desktop automation framework and scriptable UI toolkit designed for building personalized productivity tools. It serves as a cross-platform CLI wrapper and macOS system automator, providing an environment to execute scripts that manage operating system tasks, file management, and application workflows. The project distinguishes itself with a dedicated LLM integration layer for structured data extraction and text generation, alongside a specialized UI framework for creating interactive input forms, HTML windows, and floating widgets. It features deep macOS integration through AppleScr