Frameworks · curated
AdvAgent (formerly AdvWeb)
Research code for constructing and evaluating adversarial inputs to web agents, with a black-box red-team pipeline using Mind2Web data and SeeAct.
Release date not recorded · webRESOURCE CATEGORY
Computer-use agent frameworks
Browse 79 reviewed frameworks connected to computer-use, GUI, web, and mobile agents. Each entry links to primary evidence and records its scope.
Review means AI-assisted editorial inspection, not independent reproduction. Unknown licenses and specifications remain unknown.
Frameworks · curated
Agent Workflow Memory implementation
Research code that extracts reusable browser-task routines from demonstrations or prior executions, stores them as workflow memory and reuses them during subsequent navigation.
Release date not recorded · webFrameworks · curated
Agent-R
Trajectory collection and revision utilities that use tree search and model-guided critique to train agents to recover from mistakes, including WebShop tasks.
Release date not recorded · webFrameworks · curated
AgentLab
Experiment framework for developing and evaluating browser agents.
Release date not recorded · webFrameworks · curated
AgentProg
Android GUI-agent framework that keeps long-running task context in structured programs, variables and control flow, with a CLI and AndroidWorld integration.
Release date not recorded · androidFrameworks · curated
AgentStudio
Toolkit and Ubuntu-based environment for building and evaluating generalist computer-use agents through GUI and API interaction.
Release date not recorded · desktop, linuxFrameworks · curated
AgentSynth task-generation pipeline
Generates synthetic computer-use tasks and records trajectories in OSWorld desktop environments and InSTA browser environments.
Release date not recorded · desktop, webFrameworks · curated
AndroTMem inference and evaluation code
A public Android GUI evaluation framework with action-history, summary and anchored-memory prompt modes, plus step-action and dependency-aware task scoring.
Release date not recorded · androidFrameworks · curated
ARPO training framework
Replay-based policy-optimization framework for GUI agents, with distributed OSWorld rollouts and screenshot/action histories.
Release date not recorded · desktop, linuxFrameworks · curated
Browser Use
Open-source browser agent library that runs locally with any LLM against a local or cloud browser, and also serves as a CLI for coding agents and as a driver for Claude's browser toolset.
Release date not recorded · webFrameworks · curated
CHOP
Mobile automation framework that uses reusable basis subtasks to constrain and refine planning between user goals and executable actions.
Release date not recorded · android, harmonyosFrameworks · curated
ClawGUI
Framework for GUI agent training, evaluation, and deployment.
Release date not recorded · cross-platformFrameworks · curated
CoAT research implementation
Research scripts that generate screen descriptions, action reasoning and expected outcomes, then predict Android GUI actions using the resulting Chain-of-Action-Thought context.
Release date not recorded · androidFrameworks · curated
Computer Use OOTB
Gradio desktop GUI agent for Windows and macOS that needs no Docker, using Claude 3.5 Computer Use over the API or ShowUI and UI-TARS run locally, with multi-display and phone remote control.
Release date not recorded · desktopFrameworks · curated
ComputerRL
Reinforcement-learning infrastructure for computer-use agents.
Release date not recorded · desktopFrameworks · curated
Cua
Monorepo behind Cua Spaces, which gives agents full macOS or Linux desktops, plus Cua Driver for operating native apps, Lume for Apple Silicon VMs, Cua Bench and the CUA-S1 decision models.
Release date not recorded · desktopFrameworks · curated
CUAWright (formerly Webwright)
Agent framework for browser and desktop tasks using automation code.
Release date not recorded · web, desktopFrameworks · curated
D-PoT evaluation code
Offline prompting and evaluation code for Dynamic Planning of Thoughts on Android-in-the-Wild, including action extraction and comparison with reference actions.
Release date not recorded · androidFrameworks · curated
Digi-Q
Offline device-control training code that learns action values and uses them to select promising actions, with linked trajectories and checkpoints.
Release date not recorded · androidFrameworks · curated
DigiRL
Reinforcement learning for autonomous mobile device control.
Release date not recorded · androidFrameworks · curated
DistRL
Distributed online reinforcement-learning framework for Android agents, with environment setup and trajectory collection tools.
Release date not recorded · androidFrameworks · curated
DroidCall generation and evaluation code
Data-generation, fine-tuning and evaluation utilities for teaching small language models to invoke Android intents through predefined functions.
Release date not recorded · androidFrameworks · curated
Go-Browse
Structured website-exploration and data-processing code that revisits discovered pages, proposes tasks and collects trajectories for web-agent fine-tuning.
Release date not recorded · webFrameworks · curated
GroundGUI training and evaluation code
Code for screenshot grounding through supervised training, teacher-guided distillation, reinforcement learning, and benchmark evaluation.
Release date not recorded · desktop, web, cross-platformFrameworks · curated
GUI-CIDER research code
Released data-synthesis and evaluation scripts that distill planning and causal GUI knowledge into text for mid-training mobile interface agents.
Release date not recorded · androidFrameworks · curated
GUI-HARVEST
Optimizes GUI-agent execution code from repeated rollout evidence and checks proposed changes against fixed validation gates.
Release date not recorded · desktopFrameworks · curated
GUI-RC / GUI-RCPO
GUI-grounding research code for spatial voting across sampled predictions and test-time policy optimization using region-consistency rewards.
Release date not recorded · cross-platform, desktop, webFrameworks · curated
GUI-ReWalk
A desktop trajectory-generation framework that moves from stochastic GUI exploration to inferred goals and multi-stage task completion, with retrospective reasoning annotations.
Release date not recorded · desktop, linuxFrameworks · curated
GUIPivot
Query-inference training tools connecting screenshot grounding with GUI action reasoning, including preprocessing, query refinement and offline single-step evaluation on AndroidControl and AITZ.
Release date not recorded · androidFrameworks · curated
HUD
SDK for RL environments and evals spanning coding, browser, computer-use and robotics agents, whose environments expose SSH, MCP, CDP or VNC capabilities behind a minimal start-and-grade protocol.
Release date not recorded · web, desktopFrameworks · curated
HyperAgent
Library adding natural-language commands to Playwright: accessibility-tree single actions, multi-step tasks that can use screenshots, an MCP client and action caching for replay without LLM calls.
Release date not recorded · webFrameworks · curated
LaVague
Open-source web agent framework where a World Model turns an objective and the current page into instructions and an Action Engine compiles them into Selenium or Playwright code to run.
Release date not recorded · webFrameworks · curated
LiteWebAgent
Modular web-agent framework with browser control, planning, workflow memory, and tree-search components, plus web and extension interfaces.
Release date not recorded · webFrameworks · curated
MAI-UI inference and evaluation code
Published MAI-UI grounding and navigation-agent implementations with inference demos and evaluation scripts.
Release date not recorded · androidFrameworks · curated
MemGUI-Agent
MemGUI-Agent training and offline evaluation tools provide trajectory conversion, LoRA SFT templates, and step-level checks of GUI actions, memory updates and context folding.
Release date not recorded · androidFrameworks · curated
META-GUI baseline
Training and evaluation pipeline for conversational mobile GUI agents, with action prediction, response generation, and dataset processing.
Release date not recorded · unspecifiedFrameworks · curated
Midscene.js
Visual automation toolkit for web, mobile, and desktop interfaces.
Release date not recorded · cross-platformFrameworks · curated
MobileForge
Android GUI-agent adaptation framework combining app exploration, generated curricula and rollout feedback with hint-conditioned step-level GRPO; the documented public training path targets Qwen3-VL-8B.
Release date not recorded · androidFrameworks · curated
MobileRL
Online agentic RL framework for mobile GUI agents built around the difficulty-adaptive ADAGRPO algorithm, with Dockerized AndroidWorld and AndroidLab evaluation and a MobileRL-9B checkpoint.
Release date not recorded · androidFrameworks · curated
Mobilerun (formerly Droidrun)
A framework that combines screenshots and accessibility state with agent tools for mobile-device tasks through command-line and Python interfaces.
Release date not recorded · android, iosFrameworks · curated
NNetNav
Collects and labels browser-exploration trajectories for agent training, with code for data processing, fine-tuning, and web evaluation.
Release date not recorded · webFrameworks · curated
Notte
Web agent framework and cloud SDKs for managed Chrome sessions, adding a CLI, an MCP server for coding agents, serverless browser functions and an API that builds automations from English tasks.
Release date not recorded · webFrameworks · curated
OpenMobile-2 code
Evaluation adapters and training guidance for OpenMobile-2 across Android emulators and browser-rendered mobile simulation.
Release date not recorded · android, webFrameworks · curated
ORBIT framework
Inspect-based multi-agent evaluation framework with role, scheduling and communication controls, BrowserART accessibility-tree actions, and desktop mouse, keyboard and screenshot tools.
Release date not recorded · web, desktopFrameworks · curated
OS-Sentinel
Safety-checking environment and benchmark for mobile agents on AndroidWorld that judges proposed actions with rule-based and VLM-based checks, evaluated on the MobileRisk trajectory dataset.
Release date not recorded · desktopFrameworks · curated
PC-Agent-E training and deployment
Tools for refining and augmenting human computer-use trajectories, preparing supervised training data, and deploying a native PC-Agent-E scaffold.
Release date not recorded · desktop, windows, linuxFrameworks · curated
Plan-and-Act
A web-agent framework that separates high-level planning from action execution, with replanning and synthetic planner-data generation components.
Release date not recorded · webFrameworks · curated
Proposer-Agent-Evaluator (PAE)
A browser-agent training system that proposes tasks, collects visual interaction trajectories, and uses automated evaluation to drive policy improvement.
Release date not recorded · webFrameworks · curated
RedTeamCUA
A controlled testing framework that combines desktop virtual machines and replicated websites to evaluate computer-use agents against indirect prompt injection.
Release date not recorded · web, desktopFrameworks · curated
SCALE-CUA (THUDM)
Computer-use training framework with VeriGen task synthesis, adaptive rollout sampling, and visual-context segmentation.
Release date not recorded · desktopFrameworks · curated
ScreenSuite
A shared evaluation harness for GUI-model perception, offline action prediction and multi-step interaction, using simple smolagents-based agents across existing benchmarks.
Release date not recorded · web, android, desktopFrameworks · curated
Seg2Click
Training and inference implementation that predicts an executable-region mask and derives a GUI click from that mask.
Release date not recorded · cross-platformFrameworks · curated
Self-MAP
A conversational web-agent implementation with candidate ranking and memory-assisted action planning, including optional memory simplification, refinement and self-reflection modules.
Release date not recorded · webFrameworks · curated
SkillWeaver
A web-agent framework that explores sites, synthesizes reusable interaction APIs and builds a skill library for later tasks.
Release date not recorded · webFrameworks · curated
Skyvern
Browser workflow automation that relies on vision LLMs and a swarm of agents instead of fixed XPath selectors, offered as a Playwright-compatible SDK and a no-code workflow builder.
Release date not recorded · webFrameworks · curated
Stagehand
Browser automation framework combining code and natural-language actions.
Release date not recorded · webFrameworks · curated
StateAct
State-tracking prompts and experiment runners for language agents, including a WebShop implementation alongside text-based environments.
Release date not recorded · webFrameworks · curated
STEVE / STEVE-R1 research code
Research code and linked models for step-verified computer-use training; the current repository describes STEVE-R1 and its trajectory releases.
Release date not recorded · desktop, windows, linuxFrameworks · curated
Surfkit
Python toolkit and CLI for building, publishing and running multimodal agents that operate devices such as Ubuntu desktops, locally or on Kubernetes, with task trackers and an agent hub.
Release date not recorded · desktopFrameworks · curated
SwitchMem
Memory-routing implementation that chooses text or image demonstrations for a frozen GUI actor, with offline evaluation and Android transfer experiments.
Release date not recorded · androidFrameworks · curated
Synapse
A computer-control research implementation that retrieves example trajectories from memory, abstracts task-relevant state and prompts an agent to navigate browser tasks.
Release date not recorded · webFrameworks · curated
TongUI training and inference framework
Training configurations, preprocessing and inference examples for tutorial-trained GUI models, with a LLaMA-Factory fine-tuning workflow and screenshot-grounding interfaces.
Release date not recorded · cross-platform, desktop, webFrameworks · curated
TreeCUA
Framework for generating GUI trajectories through tree-structured exploration and verification.
Release date not recorded · desktopFrameworks · curated
UI-Genie
Training and evaluation code for a mobile-agent framework that iteratively generates trajectories using agent and reward-model feedback.
Release date not recorded · androidFrameworks · curated
VEM GUI-Agent-RL
Training code that learns a value environment model from offline Android interaction data and uses its frozen value estimates to guide GUI policy optimization.
Release date not recorded · androidFrameworks · curated
VeriOS
Research code for proactive human–GUI-agent verification, including offline interaction-loop and dual-agent evaluation scripts plus LLaMA-Factory fine-tuning configurations.
Release date not recorded · unspecifiedFrameworks · curated
VeriSafe Agent
Runtime verification framework for Android GUI agents that checks proposed actions against logical rules derived from user instructions and developer-defined app states.
Release date not recorded · androidFrameworks · curated
VideoCAD training and evaluation code
VideoCADFormer training, action-log preprocessing and evaluation code for learning CAD interface action sequences from screen recordings of browser-based Onshape.
Release date not recorded · webFrameworks · curated
WebAgent-R1
Environment setup, multi-turn reinforcement-learning and evaluation tooling for browser agents interacting with WebArena.
Release date not recorded · webFrameworks · curated
WebDreamer
World-model and planning components that simulate web-action outcomes, with linked training data and model checkpoints.
Release date not recorded · webFrameworks · curated
WebEvolver code component
Component for web-agent trajectory collection, supervised-data preparation and world-model-based trajectory synthesis.
Release date not recorded · webFrameworks · curated
WebLlama
Training, evaluation and integration tooling for dialogue-guided web agents, including Llama fine-tuning workflows and BrowserGym examples built around WebLINX.
Release date not recorded · webFrameworks · curated
WebRL
Training pipeline that evolves web tasks from prior attempts and uses an outcome reward model to refine browser policies.
Release date not recorded · webFrameworks · curated
WebVLN research implementation
Training and evaluation code for question-guided website navigation that combines visual observations with web-specific HTML information.
Release date not recorded · webFrameworks · curated
WinDOM code
GUI-grounding training and evaluation code with same-family distillation, GRPO recipes and point-in-box scoring, using a Windows-style web environment.
Release date not recorded · webFrameworks · curated
Work2Skill
Collects human GUI demonstrations and inspects multimodal evidence to derive reusable agent workflow skills.
Release date not recorded · desktop, macos, linuxFrameworks · curated
Workflow-Guided Exploration research code
Research code that learns browser-control policies by constraining exploration with workflows induced from demonstrations, with a Selenium-based MiniWoB environment and experiment harness.
Release date not recorded · webFrameworks · curated
WorkForceAgent-R1
Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.
Release date not recorded · webFrameworks · curated
ZeroGUI
Online RL framework for GUI agents in which VLMs generate the training tasks and judge success from trajectory screenshots, with OSWorld and AndroidLab checkpoints trained from UI-TARS-7B-DPO.
Release date not recorded · cross-platform