← Tags

#Computer Use (13)

WaterfallPagination

web-infra-dev/midsceneMIT

Midscene.js: A Vision GUI Agent and E2E Testing Framework

ByteDance Web Infra open-source vision GUI agent and E2E testing framework. It locates elements from screenshots instead of selectors and drives Web, Android, iOS, HarmonyOS and desktop through one API, shipping YAML cases, TypeScript nodes, replayable reports and CLI skills for coding agents. An agent-harness layer, not an AI-coding tool.

Agent HarnessGUI AgentE2E Testing

TypeScript15k1.2k70

CopilotKit/OpenDotsMIT

CopilotKit open-sources OpenDots: self-hostable always-on AI coworkers — each Dot gets its own computer, moving between text, voice calls and Slack, works with any agent harness

CopilotKit open-sourced OpenDots (MIT) on Oct 1: a fully self-hostable template for always-on AI coworkers — its answer to OpenAI's closed Dots (powered by GPT-6 Astra). Each Dot is a specialist agent with a name, role, instructions and tool allowlist, plus its own computer via OpenBot's container supervisor (browser profile and workspace files persist across stop/start). Dots move seamlessly between text chat, realtime voice calls and Slack: calls pair a separate compute agent so long work keeps running mid-conversation, all sharing the same context and tool permissions. AG-UI carries streamed messages, tool calls and agent state between any agent harness and the UI; human-in-the-loop cards pause tool calls for approval; Spaces and Pages hold working documents. Built on TanStack AI + CopilotKit React SDK + Threads + Channels SDK. Clone and customize — enterprise-ready.

HarnessAgent-WorkspaceCopilotKit

TypeScript591733

0:40

iPhone Use: Codex Controls a Real iPhone Over USB

@zhongerxin · 220 views · 2026-10-08

Mobile AgentComputer UseOpen Source

0:30

LCU: Expose Codex Computer Use to Any Agent

@dotey · 363 views · 2026-10-05

Computer UseGUI AgentMCP

0:08

Taiga-S1: a 1.2M-param model builds complete CAD parts in FreeCAD — ~1ms per decision on CPU, no LLM, no screenshots. Your agent plans, Taiga executes

@RoundtableSpace · 669 views · 2026-10-01

DesignCADFreeCAD

0:45

Open-Dots: an open-source version of the new OpenAI Dots agent you can run yourself

@matchaman11 · 911 views · 2026-09-29

Open-DotsOpenAIDots

1:37

OpenMausBot: a self-hostable team of AI agents

@BuildwithOmkarr · 722 views · 2026-09-23

OpenMausBotAI AgentComputer Use

1:23

Meta Introduces Muse, a Personal AI Agent That Gets Things Done

@Muse · 627 views · 2026-09-08

AgentComputer UsePersonal Assistant

1:06

OpenMuse: An Open-Source, Self-Hostable Personal AI Assistant

@ataiiam · 810 views · 2026-09-22

AgentComputer UseOpen Source

MiMo-V2.6 Deep Read: Six Days of Live RL, an AA Index of 46 and a Fully Open Self-Improvement Run

Xiaomi open-sources MiMo-V2.6 Pro/Flash: 30 live RL steps, ~750k trajectories at $850k/$2.62M; AA Index 46 tops open models, DeepSWE v1.1 gains +17/+14 out of sample; Vibe World, CUA, science and content demos plus 7k+ RL environments released.

BLOG

LLMXiaomi MiMoReinforcement LearningAgentic RLOpen-source LLM

How does Astra's computer use actually work?

A source-code grounded walkthrough of GPT-6 Astra: accessibility trees instead of pixel guessing, a persistent Node REPL, actions written as code, and a Guardian policy that blocks risky operations before execution.

BLOG

Computer UseAI AgentGPT-6 AstraOpenAICodex

1:46

Xiaomi MiMo Desktop enters invite-only beta as a desktop agent

@XiaomiMiMoDevs · 683 views · 2026-09-08

Desktop AgentXiaomiMiMo

0:19

Microsoft Fara 1.5 Computer-Use Models (4B/9B/27B)

@HuggingApps · 375 views · 2026-07-28

Computer UseGUI AgentMultimodal

As an Amazon Associate, we earn from qualifying purchases.