manaflow-ai/manaflow

Open source Claude Code web/Codex Cloud/Devin/Ramp Inspect alternative

What it solves

Manaflow provides a way to run multiple AI coding agents (such as Claude Code, Codex CLI, and Gemini CLI) simultaneously on a single codebase. It eliminates the need to manage separate terminals or environments for different AI tasks, allowing developers to verify and ship code changes faster through parallel execution.

How it works

The system spawns each agent in an isolated, sandboxed VS Code workspace—either in the cloud or via a local Docker container. Each workspace includes a terminal, a git diff view, and a dev server preview. This allows the user to monitor the agent's progress in real-time and review changes via a heatmap diff viewer before creating pull requests.

Who it's for

Software engineers and developers who use AI coding agents and want to increase productivity by running multiple agents in parallel across different tasks.

Highlights

  • Parallel Agent Orchestration: Run multiple different coding agents at once with custom prompts and model selection.
  • Isolated Workspaces: Every agent operates in its own sandboxed environment with full VS Code and terminal access.
  • Live Web Preview: An embedded browser allows users to see dev server output and app changes in real-time.
  • Integrated PR Workflow: Review diffs and open pull requests directly from the workspace.
  • Workspace Monitoring: A unified view of the VS Code editor, agent TUI, and VNC browser preview.

Related

  • Project
    madarco/agentbox

    A tool for running multiple AI coding agents in parallel using isolated, sandboxed virtual environments hosted locally or in the cloud.

  • Project
    Mng-dev-ai/agentrove

    A self-hosted AI coding workspace that orchestrates multiple AI agents from one interface, providing sandboxed environments and multi-agent workflows.

  • Project
    kdlbs/kandev

    An open-source orchestrator for AI coding agents that enables parallel task execution, remote runtimes, and a unified review-first workspace.

  • Project
    stablyai/orca

    An AI orchestrator that lets developers run multiple CLI agents side-by-side in isolated worktrees with a mobile companion app for remote monitoring.

  • Project
    Untrivial-ai/agent-orchestrator

    Agent Orchestrator is a cross‑platform desktop app that lets you run multiple LLM‑based coding agents as isolated Git‑backed workers, coordinate them via a project‑level orchestrator, and monitor everything on a live Kanban board.