cubeplexai/cubeplex

CubePlex is a cloud-native platform for managed agents in team workspaces — skills, shared memory, MCP tools, persistent sandboxes, governed access, and self-hosted deploy on Docker Compose or Kubernetes.

What it solves

CubePlex provides a cloud-native platform for creating and managing long-lived AI agents that are owned by teams rather than individuals. It solves the problem of fragmented agent state by ensuring that a team's agent maintains a stable role, shared knowledge, and a persistent work environment across different tasks and communication channels.

How it works

The platform uses a dedicated "Workspace" concept where a team's agent resides. This agent is powered by the CubeLoop framework for async-native execution and multi-provider model access. Each workspace is equipped with an isolated sandbox with persistent storage, allowing the agent to keep files, packages, and its working tree intact across restarts. The system integrates with various IM platforms (Slack, Discord, Teams, etc.) and supports Model Context Protocol (MCP) tools, allowing the same agent to be accessed via multiple entry points while maintaining a shared state.

Who it’s for

It is designed for teams and organizations that need a collaborative AI agent that serves as a stable team member with shared memory and governed tools, rather than a series of disconnected personal AI assistants.

Highlights

  • Team-owned state: Agent configuration, knowledge, and working state belong to the workspace, not the person.
  • Persistent sandboxes: Isolated runtimes with storage that survives restarts.
  • Omnichannel access: One agent accessible via web, Slack, Discord, Teams, and other IM bridges.
  • Governed MCP tools: Admin-curated tool catalogs with flexible credential scoping (org, workspace, or user).
  • Layered memory: Ability to recall personal preferences, shared workspace facts, and organization-wide policies.
  • Artifacts: Direct delivery of versioned files, code, and images within conversations.

Related

  • Project
    Team-Commonly/commonly

    Commonly is an open‑source, self‑hosted platform that lets humans and AI agents share a persistent workspace (“pod”) with chat, memory, a task board, and tool integrations. Agents join as named seats, keep their own identity and runtime, and can be connected via a daemon, manual CLI, or MCP package. The system includes multi‑LLM routing, GitHub‑synced tasks, scoped grants for external services, and a marketplace of pre‑built agents. It runs on Docker‑Compose locally or via Helm on Kubernetes, is Apache‑2.0 licensed, and provides extensive docs and community support.

  • Project
    cloudflare/agents

    Cloudflare Agents is a TypeScript SDK that turns Cloudflare Durable Objects into persistent, stateful “agents” with built‑in real‑time sync, scheduling, AI chat, tool execution, voice, email, payments, and more. It provides decorators for RPC, React hooks for the frontend, and a suite of packages for chat, code‑generation, and dynamic Workers. Ideal for per‑user assistants, collaborative apps, voice bots, and workflow engines.

  • Project
    vfarcic/dot-ai

    An npm‑published Node library that adds LLM‑driven assistants to Kubernetes/DevOps workflows. It provides a CLI and a managed platform (MCP) for natural‑language cluster queries, deployment recommendations, automated remediation, policy‑driven prompt libraries, and semantic doc search, all packaged for easy installation on a Kubernetes cluster.

  • Project
    Yuan-lab-LLM/ClawManager

    ClawManager is a Kubernetes‑native platform that lets teams provision, manage, and govern AI‑agent workspaces (OpenClaw, Hermes, OpenCode, DeepSeek Harness) via a web console and a secure northbound API. It offers Lite (shared pool) and Pro (dedicated pod) modes, AI Gateway model governance, reusable skill/resource packs, team collaboration tools, and a dedicated security‑protection console, all built with Go, React, and standard Kubernetes resources.

  • Project
    dapr/dapr-agents

    Dapr Agents is a Python framework that makes it easy to build reliable, scalable AI agents using LLMs. It leverages Dapr's built-in messaging, state, and durable workflow capabilities to guarantee your agent tasks complete — even across failures — while keeping costs low through scale-to-zero virtual actors. It auto-discovers tools from MCP servers, connects to 50+ data sources, and runs natively on Kubernetes. Currently in development for Python, with stable release expected Q4 2025.