Projects sharing features with OSWorld

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

Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che

This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals. The framework emphasizes multi-agent system orchestration through distributed architectures where specialized agents collaborate using standardized communication protocols. It details specific design patterns such as dual-memory systems for maintaining short-term plans and

This project provides a comprehensive framework for building, deploying, and orchestrating autonomous agents within a decentralized network. It serves as a collection of patterns and examples for developing intelligent software entities capable of performing complex tasks, making decisions, and interacting with other agents to achieve shared goals. The framework distinguishes itself through its focus on multi-agent orchestration and decentralized communication. It enables the coordination of specialized agent teams that collaborate on workflows through structured messaging protocols, allowing

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

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

AI-Researcher is an LLM research automation framework and scientific workflow orchestrator designed to automate the end-to-end discovery process. It employs autonomous AI research agents to identify research gaps, formulate hypotheses, and execute scientific discovery workflows independently. The system integrates an automated literature review tool for gathering and analyzing academic papers and code repositories with an AI-driven manuscript generator that synthesizes research motivations and experimental results into full-length academic papers. The framework covers a modular research pipe

This project provides a translation layer and set of adapters designed to bridge AI agents with the Model Context Protocol. It functions as an integration layer that allows agents to operate as protocol-compliant servers and enables the conversion of protocol-based tools into formats compatible with agent frameworks and logic graphs. The adapters facilitate tool interoperability by wrapping external protocol tools for use within agent workflows and exposing internal agent capabilities to any client implementing the Model Context Protocol. This creates a communication bridge that supports inte

AgentOps is an observability platform and developer toolkit for monitoring the execution, performance, and reliability of autonomous agents powered by large language models. It serves as a system for tracking AI agent behavior, debugging complex workflows, and benchmarking model performance. The platform is distinguished by its ability to visualize multi-agent workflows through execution path graphing and session replays. It provides specific tools for calculating financial spend across various language model providers and supports a self-hosted observability stack for users who require full

KeymouseGo is an input automation tool and macro recorder designed to capture, edit, and replay keyboard and mouse sequences to automate repetitive desktop tasks. It functions as a scriptable input automator that translates recorded user interactions into reusable blueprints for automated playback. The system distinguishes itself through a logic-based scripting framework that supports conditional branching, sub-routine calls, and jump-to-labels for complex workflow control. It further extends runtime behavior via a plugin system that allows for the registration of custom functions to modify t

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

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

Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development tasks. It functions as a comprehensive system for automating coding, testing, and repository management by integrating directly with your codebase and terminal. The platform provides a unified gateway for model orchestration, allowing for the management of agentic workflows, event-driven automation, and persistent session state across distributed development environments. The platform distinguishes itself through its federated task management and policy-based access control, which

Universe is a training and evaluation platform that transforms websites, games, and software into standardized environments for general intelligence agents. It functions as a reinforcement learning wrapper and remote environment orchestrator, providing a consistent interface to wrap diverse software for AI agent interaction. The platform distinguishes itself through a visual observation interface that streams real-time pixel data and transmits keyboard and mouse events to simulate human interaction. It utilizes a bi-directional communication protocol to deliver reward signals and performance

MiroThinker is an autonomous research system that uses large language models to perform deep research and predictions through iterative reasoning. It functions as a web-search AI framework capable of retrieving real-time internet data and scraping web content to provide verifiable sources for complex queries. The system includes a multimodal content processor that converts images, audio, and video into text descriptions for analysis by text-based models. To ensure computational accuracy, it utilizes a sandboxed code executor for running Python code and data analysis. Performance is managed th

This project is a comprehensive framework for building, evaluating, and connecting autonomous agent systems. It provides a library of standardized architectural patterns for implementing complex agent workflows, including multi-agent orchestration, iterative reasoning, and memory management. By offering a unified interface for model providers, the framework allows for consistent agent execution across different artificial intelligence services. The framework distinguishes itself through a focus on rigorous benchmarking and deterministic control. It includes a suite of tools for evaluating age

LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it

This project is a language model evaluation framework and benchmarking tool designed to measure the accuracy and performance of models across diverse datasets. It provides a system for implementing model-based graders, running standardized tests for mathematical reasoning, coding, and factuality, and calculating quantified performance metrics such as precision, recall, F1 scores, and pass-at-k. The framework utilizes model-based grading and rubrics to validate response quality against expert-defined criteria. It includes a multi-model benchmarking loop and a model-agnostic API interface to co

WebAgent is an autonomous web navigation agent and research system designed to browse the internet and synthesize information to answer complex queries. It functions as a reasoning orchestrator that navigates the web iteratively to perform deep research and extract structured data. The project includes a reinforcement learning training pipeline that generates synthetic interaction datasets for model pre-training and fine-tuning. It employs token-level policy gradients to stabilize training in non-stationary environments and uses a dual-mode inference scaling mechanism to balance execution bet

vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys

mini-swe-agent is an autonomous software engineering system designed to develop features and fix bugs by combining large language models with a bash interface. It operates as an agentic framework that executes coding tasks and documentation updates through a continuous cycle of model reasoning and tool execution. The project differentiates itself with a strong focus on safety and evaluation, utilizing container-based sandbox execution via Docker or Singularity to isolate command execution. It includes a batch-parallel evaluation harness to measure code-fixing accuracy against standardized sof

This project is a TypeScript software development kit designed for building and orchestrating autonomous agents that interact with codebases and system environments. It provides a programmatic interface for constructing agents capable of executing complex workflows, such as automated code refactoring, file system manipulation, and shell command execution, by leveraging large language models. The framework distinguishes itself through a focus on secure, governed agent operations. It includes granular access control systems that allow developers to define specific permissions for tools and exte

xdotool is a command-line utility for X11 desktop automation that simulates keyboard and mouse input and manages application windows. It functions as a scriptable tool that maps sequential text instructions to low-level library calls to control the X11 graphical environment. The project enables the generation of synthetic keyboard and mouse events to automate interactions with graphical user interfaces. It also acts as a window manager controller, allowing users to programmatically move, resize, focus, and organize application windows and virtual desktops. The tool covers a wide range of cap

This project is a cross-platform input interception library and global keyboard event simulator for Windows and Linux. It provides a programmatic interface to monitor global keyboard events, simulate hardware input, and block system events to create custom hotkeys and shortcuts. The tool functions as a keyboard macro automation utility and a text expansion engine. It can record keystroke sequences and replay them with precise timing, or detect specific typed character sequences and replace them with predefined strings using simulated backspaces. The library covers a broad range of input cont

Redox is a POSIX-compliant, microkernel-based operating system written entirely in Rust. By utilizing a memory-safe language for the kernel and all system components, the project eliminates common vulnerabilities such as buffer overflows and use-after-free errors. Its architecture relies on a minimal kernel that manages only essential hardware and process isolation, delegating all other system services to unprivileged user-space processes. The system distinguishes itself through a modular design where hardware drivers and system services run as independent user-space daemons, allowing them to