vicoa-ai/vicoa

Vicoa is the agentic IDE for running a team of coding agents from desktop, mobile, VPS. Open-source, self-hostable.

What it solves

Vicoa is an AI orchestrator designed to manage a team of coding agents across multiple devices. It eliminates the need to hunt through terminal tabs or switch machines to steer your AI developers, providing a unified command center for sessions running on various servers or local machines.

How it works

It operates as a self-hostable stack consisting of a backend API, a local daemon, and multiple clients (Web, Desktop, Mobile). The local daemon spawns and manages the CLIs of various coding agents (such as Claude Code, Codex, and others via the Agent Client Protocol). Each agent session is isolated in its own git worktree and branch to prevent conflicts during parallel work.

Who it’s for

Developers who use multiple AI coding agents and want to coordinate their work from a desktop, mobile device, or CLI, and who prefer a "bring your own key" approach to model subscriptions.

Highlights

  • Multi-Agent Support: Built-in integration for 40+ coding agents, including Claude Code, Cursor, and GitHub Copilot.
  • Cross-Device Sync: Start a session on a laptop and continue steering it from iOS or Android apps with real-time sync.
  • Parallel Worktrees: Runs agents on separate git branches to allow simultaneous work on the same repository.
  • Remote Execution: Ability to connect multiple machines (VPS, remote servers) and choose where each session runs.
  • Integrated Tooling: Includes inline diffs, a file browser, a terminal, and mobile live previews for local development websites.

Related

  • Project
    terrier-org/pyterrier

    A framework for building and evaluating information retrieval pipelines, supporting sparse and dense retrieval, neural reranking, and RAG use-cases.

  • Project
    IBM/aihwkit

    A Python toolkit for simulating and using analog in-memory computing devices to eliminate the von Neumann bottleneck and improve AI energy efficiency.

  • Project
    CyberAgentAILab/cmaes

    A practical Python library implementing CMA-ES and its variants for black-box optimization of continuous, integer, and categorical variables.

  • Project
    ExtractPDF4J/ExtractPDF4J

    A production-focused Java library for extracting structured tables from text-based, scanned, and image-heavy PDFs using OCR and table structure detection.