Open-Source Computer-Use and Browser Agents

Halo is a desktop AI workstation for people who want agents to write code, manage files and handle recurring work through a visual interface. You can switch between Claude Code and Codex within the same app.

ZeroToken is a local browser automation server for people using AI agents to repeat web tasks such as collecting reports, logging into sites or testing browser workflows. It turns recorded actions into scripts so later runs don't need an LLM to reason through every step again.

Navigator is a self-hosted AI workspace for individuals and teams who want assistants to carry out tasks through connected tools. It combines chat with custom agents and reusable visual workflows.

OpenBitFun is a desktop AI agent workspace for coding and other tasks that use files and shell commands on your machine or a selected SSH host. It runs on Windows, macOS and Linux. Model requests go to the configured provider; built-in cloud connections send them to external services, and custom providers are also supported.

Phone Harness connects an AI agent to a real iPhone or Android to carry out tasks through app screens. It's for developers who want phone automation without relying on an app API.

Selene is a desktop AI agent app for coding, browser tasks and personal assistants. You can choose local or cloud processing separately for chat, embeddings, voice and image generation.

Yoji is an AI desktop companion for people who want a conversational assistant that can also act on their computer. It combines a customizable personality with file handling and task automation.

CamoFox Browser is a self-hosted browser server for developers whose AI agents need to interact with sites that detect browser automation. It builds on Camoufox, a Firefox fork with browser fingerprint spoofing, to reduce detection by systems such as Cloudflare and Google's bot checks.

Everywhere is a desktop AI assistant for people who want help with the app they're working in without copying its contents into a separate chat. It reads on-screen context to answer questions and carry out tasks across apps.

GenericAgent runs tasks on your computer using cloud models to decide what to do. It's for people who want an AI agent to work across websites, files and desktop apps, then save successful workflows for reuse. Model calls require API keys and an internet connection, with requests going to the selected provider. It supports Claude, Gemini, Kimi and MiniMax.

Octop is a self-hosted AI assistant for households and small teams that want personal agents in a shared deployment. Each user can switch between specialists with separate workspaces, model connections and scheduled tasks.

usecomputer lets AI agents interact with desktop applications through screenshots, mouse actions and keyboard input. It's for developers who want computer control in agent workflows, including those built around OpenCode or Claude Code.

DeerFlow is a self-hosted AI agent application for research, coding and content creation on your own infrastructure. It supports local models through Ollama and vLLM, including Qwen3, as well as hosted providers. With a cloud provider, model requests leave your server and may incur provider charges.

Mobile MCP connects AI agents to native iOS and Android apps for testing, form entry and extracting data from screens. Developers and testers can use the same tools across physical devices, simulators and emulators.

CoWork OS is an AI agent desktop for developers and people working with documents, research and email. It brings tasks and their outputs into one workspace, where you can review agent actions and control approvals.

QuickDesk is a remote desktop app that lets AI agents operate other computers through a built-in MCP server. Developers and administrators can automate desktop tasks while watching the agent's actions and intervening when needed.

BrowserWing is a local browser automation tool for developers and AI agent users who need repeatable website tasks and structured data. It lets you record a workflow once and make it available to agents as a reusable action.

LobsterAI is a desktop AI agent built on OpenClaw for office work and local projects. It operates tools on your computer and keeps sessions, configuration and memory there. You select each agent’s model separately from its workspace and tools.

Hermes Browser Extension puts an existing Hermes Agent in a browser side panel for people who want to ask about the pages they're reading. Page context works through local or remote API connections; Hermes Cloud and dashboard-ticket connections are chat-only.

BrowserPilot is a Python browser automation agent for developers who want to describe web tasks in plain English. It controls Chrome through Selenium on your machine, or a remote browser through Selenium Grid. The software is open source under the MIT license, but its AI capabilities use OpenAI's cloud API and require an API key and internet access.

Atomic Agent is a local AI agent for people who want an assistant to work with their browser, files and code on their own hardware. Its model and task loop can run offline, while sessions and memory stay on disk. It's free and open source under the MIT license.

Open Interpreter is a locally installed terminal coding agent for developers on macOS, Linux and Windows. It's a fork of OpenAI's Codex that focuses on adapting agent behavior to lower-cost models. Commands run on your computer inside native sandboxing; model requests go to your selected provider, so local installation alone doesn't mean local inference.

Agentlas OS is an open-source AI agent framework for projects that need specialist teams and shared project context. It runs on macOS, Windows and Linux, with local document indexing, semantic search and memory retrieval. You supply the model. Using a cloud model sends requests to that provider and may incur charges.

ProofShot is a local browser verification CLI for developers reviewing UI work produced by AI coding agents. It saves browser interactions and errors as review artifacts so you can inspect what the agent tested.

WeKnora is a self-hosted AI knowledge platform for teams that want to query documents, carry out tasks using them and organize them into a wiki. These functions share the same knowledge bases.

Leon is a personal AI assistant for people who want to automate tasks on their own computer or server. Its skills let you add actions suited to your needs.

Auto Browser lets AI agents operate a live browser that a human can take over when a login or fragile page needs attention. It's built for internal dashboards, account workflows and operator-assisted browser QA.

Steel is a browser API for developers building AI agents that interact with websites. It supplies real Chrome sessions for tasks involving clicks, forms, logins and pages that rely on JavaScript.

Skales is an AI agent for people who want help with files, browsing, email and coding on their own devices. It can keep working on a goal after you close the chat and resume unfinished goals after a restart.

Open Science Desktop brings research agents, notebooks and project files into one workbench for researchers who want to inspect the work behind an AI-generated result. Agents can carry a research topic through literature review, experiments, analysis and manuscript writing.

PocketPaw is a self-hosted AI agent for people who want an assistant to write code, manage files and act on websites from their own computer or server.

AIRecon automates penetration testing and bug bounty reconnaissance for security testers. It guides an assessment through reconnaissance, analysis, exploitation and reporting, with a terminal interface for following the agent's work.

OpenBrowser is a self-hosted browser automation agent for people who need visual judgment and interaction across web pages. Its server and Chrome extension run locally, but the documented Qwen setup sends model requests to DashScope's cloud API and requires an API key and internet access. Browser execution stays local; model processing uses the remote provider.

Skyvern automates browser tasks for teams handling forms, vendor portals and repeated data collection. It uses vision models to identify page elements, helping workflows adapt when website layouts change.