What is CubePlex used for?

CubePlex is a self-hostable platform for team workspaces where a long-lived AI agent has shared skills, memory, MCP tools and persistent sandboxes, reachable from the web and chat apps. It is a good fit for shared AI assistant for a team and governed agent automation in enterprise workspaces.

Is CubePlex open source?

Yes. CubePlex is open source under a custom licence. Its source code is on GitHub at cubeplexai/cubeplex and is written mainly in Python.

Yes. CubePlex is open source, so the software itself is free to use under the terms of its own licence.

Can I self-host CubePlex?

Yes. CubePlex can be self-hosted on your own server or infrastructure.

What is CubePlex an alternative to?

CubePlex is an open-source alternative to Lindy. Other open-source alternatives to Lindy include Magic, Agenta and AutoGPT.

Is CubePlex actively maintained?

Yes. The most recent commit to CubePlex was on 2 October 2026, and the latest release is v0.9.0, published on 28 September 2026. The project has 508 stars on GitHub.

CubePlex: open-source alternative to Lindy

About CubePlex

CubePlex is a cloud-native platform for managed AI agents that belong to a team rather than an individual. Each workspace gets one long-lived agent with a stable role, shared knowledge, approved tools and a persistent working environment, so the team returns to the same agent across tasks.

The agent can be used from the web and from messaging channels including Slack, Discord, Teams, Feishu, DingTalk and WeCom, with each conversation keeping its own participants and context. Skills, shared memory and MCP connections are configured per workspace, and isolated persistent sandboxes plus organization-level controls keep the agent's work inspectable and governed.

The agent runtime is built on CubeLoop, an async agent framework covering multi-provider model access, tool execution, streaming, middleware and durable checkpoints. External model providers, MCP servers and chat platforms stay outside CubePlex's trust boundary. It is written in Python and can be deployed with Docker Compose or Kubernetes. The licence is listed as other.

Key features

One long-lived agent per team workspace
Shared skills, memory and MCP tools
Persistent isolated sandboxes
Access from Slack, Discord, Teams and more
Organization-level governance controls
Docker Compose and Kubernetes deployment

Good fit for

→Shared AI assistant for a team
→Governed agent automation in enterprise workspaces

Built with: Python
Tags: ai-agents; self-hosted; mcp; workspace; kubernetes; docker; sandbox; enterprise

CubePlex: questions and answers

What is CubePlex used for?: CubePlex is a self-hostable platform for team workspaces where a long-lived AI agent has shared skills, memory, MCP tools and persistent sandboxes, reachable from the web and chat apps. It is a good fit for shared AI assistant for a team and governed agent automation in enterprise workspaces.
Is CubePlex open source?: Yes. CubePlex is open source under a custom licence. Its source code is on GitHub at cubeplexai/cubeplex and is written mainly in Python.
Is CubePlex free?: Yes. CubePlex is open source, so the software itself is free to use under the terms of its own licence.
Can I self-host CubePlex?: Yes. CubePlex can be self-hosted on your own server or infrastructure.
What is CubePlex an alternative to?: CubePlex is an open-source alternative to Lindy. Other open-source alternatives to Lindy include Magic, Agenta and AutoGPT.
Is CubePlex actively maintained?: Yes. The most recent commit to CubePlex was on 2 October 2026, and the latest release is v0.9.0, published on 28 September 2026. The project has 508 stars on GitHub.