openkursar/hello-halo

7×24 Desktop AI Agent for Everyone. Visual AI assistant with remote access, file management, and built-in AI browser.

What it solves

Halo is an AI workstation designed to move beyond simple chat interfaces by providing a local environment where AI agents can autonomously execute tasks. It solves the problem of needing to constantly monitor AI outputs or manually bridge the gap between an LLM and actual system operations (like coding, web browsing, and terminal usage) for both technical and non-technical users.

How it works

Halo uses a pluggable engine architecture that supports various agent engines such as Claude Code and Codex. It integrates several key tools into a single interface:

  • AI Browser: An embedded browser that the AI can control via JavaScript-based "Browser Actions" to perform precise operations on web platforms.
  • AI Terminal: A persistent terminal allowing the AI to operate CLI tools, SSH into servers, and run code.
  • Knowledge Base: A local RAG system where users can drop files (PDF, PPT, Markdown) for the AI to reference.
  • AI Digital Humans: Autonomous agents that can be scheduled to run 24/7, utilizing the browser, terminal, and messaging apps (WeChat/WeCom) to handle routine operations.

Who it’s for

  • Developers who want a visual, remote-accessible interface for agentic tools like Claude Code.
  • Enterprise teams requiring 100% local deployment for data compliance.
  • Non-technical users who want to automate web-based workflows and social media management without writing scripts.

Highlights

  • Local-First: Zero cloud dependency; data stays on the machine.
  • Remote Access: Control the workstation and its agents from a mobile device or IM app.
  • Autonomous Workforce: Schedule AI "Digital Humans" to perform recurring tasks like monitoring, reporting, and content publishing.
  • Pluggable Engines: Compatible with MCP and various frontier LLM providers (Anthropic, OpenAI, DeepSeek).
  • One-Click Install: Distributed as a desktop application with no backend or Node.js configuration required for the end user.

Related

  • Project
    holaboss-ai/holaOS

    An agentic workspace that integrates AI agents side-by-side with real applications and chat tools, featuring local-first memory and shared tool access.

  • Project
    chadbyte/clay

    Clay Studio is a self‑hosted web workspace that lets humans and locally‑installed AI coding agents (Claude, Codex, Copilot CLI, etc.) collaborate in shared, persistent sessions. It runs a Node daemon on your machine, serves a browser UI, stores project state on disk, and routes requests to the agents’ own CLIs, keeping code and context under your control while enabling real‑time teamwork and background automation.

  • Project
    shiwenwen/hope-agent

    Hope Agent is a Rust‑based, desktop‑first AI assistant that can run as a native GUI, a headless server with a web UI, or an IDE‑integrated backend. It supports long‑term memory, goal‑driven autonomous task planning, design‑artifact generation, and tool‑calling (OS control, shell, MCP, etc.). Install via Homebrew, Scoop, apt/dnf, or Docker; it works on macOS, Linux and Windows (experimental).

  • Dispatch
    Halo: Open-Source Tamper-Evident Runtime Evidence for AI Agents

    Halo is an open-source framework that creates hash-chained, tamper-evident runtime records of AI agent actions to provide verifiable audit trails for security and compliance reviews.

  • Project
    PM-Shawn/Abu-Cowork

    A locally-run AI desktop assistant that autonomously plans and executes office tasks, manages local files, and runs commands with a focus on privacy and security.