SuperAPI AI Directory

moltbot

OpenClaw (formerly moltbot) is an open-source AI assistant that runs on the user's own computer and connects to more than 20 chat channels including Discord, iMessage, Slack, Teams, Telegram, WhatsApp, and more, while also offering native apps for macOS, iOS, Android, Windows, and Linux. It is managed by a local Gateway as the control plane for sessions, tools, events, and channel connections, with state, memory, and credentials stored on the user's hardware; the model and agent frameworks (Claude, Codex, local models) are replaceable as plugins. The project is governed by the independent OpenClaw Foundation (501(c)(3)), with no paid tiers, hosted services, or tokens.

Open website

About this tool

OpenClaw (repository name moltbot) is an open-source AI assistant positioned as "an AI that can actually get things done," supporting any operating system and platform. It runs on the user's own computer and appears in the chat channels users already use, including more than 20 channels such as Discord, iMessage, Slack, Teams, Telegram, and WhatsApp, while also offering native apps for macOS, iOS, Android, Windows, and Linux.

Key capabilities and architecture:

  • Gateway is the local control plane, responsible for sessions, tools, events, and channel connections.
  • Control UI, CLI, and TUI connect to the Gateway.
  • Channels bring the assistant to messaging services such as WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, and more.
  • Companion apps and nodes add voice, Canvas, camera, screen, and device-local operations on supported platforms.
  • Supports hosted and local model providers; tools, skills, and plugins extend the assistant's capabilities.
  • Models and agent frameworks (Claude, Codex, local models) are plugins that can be replaced without changing anything else.

How to use: The installer supports macOS, Linux, and Windows, and configures a supported Node.js runtime when necessary. If you already manage Node.js, you can install the published package (requires Node 24.16+ or 26.1+, Node 26 recommended). The command works with npm 12 or npm 11.16+; on npm 11.15 and earlier, omit --allow-scripts=openclaw. On a fresh install, the install script automatically launches the onboarding flow; complete the wizard. If you install the package directly with npm, pnpm, or Bun, run the corresponding command. The onboarding flow verifies model access, creates a workspace, and configures the Gateway; the final command opens the Control UI, where sending a message confirms the assistant is working properly.

Security and privacy: State, memory, and credentials are stored on the user's hardware. Prompts are sent to the user's configured model provider and chat platform, as well as to any diagnostic exports the user has enabled; by default, OpenClaw It only performs a daily version check by itself; anonymous feature telemetry is opt-in, and setting update.checkOnStart: false disables both at the same time. Inbound messages should be treated as untrusted input; channels that support direct messages pair unknown senders by default, and pairing requests can be approved with openclaw pairing approve <channel> <code>. Unless a sandbox is configured, tools run on the host for the main session; before connecting other users or exposing the Gateway remotely, you should read the security guide, the exposure runbook, and the sandbox guide.

Development and governance: The repository is a pnpm workspace, and running npm install directly at the repository root is not supported. OpenClaw is developed publicly by the independent OpenClaw Foundation (501(c)(3)); the foundation employs the core team and signs releases. Donors and infrastructure sponsors support the foundation but do not own or direct the project, and OpenAI is a donor rather than an owner. New capabilities should generally be placed in plugins built on the plugin SDK and shared through ClawHub. The project uses the MIT license.

Use cases: It is suitable for individual users who want to run it on their own devices and use an AI assistant within existing chat channels, and it is also suitable for scenarios that require a shared team deployment - the same Gateway can serve as a personal assistant on a laptop or as a team deployment, with the only difference being configuration.

Limitations: The materials do not provide specific charging, pricing, or paid tier information; no hosted service or token is provided. Some features (such as voice, Canvas, camera, screen, etc.) are only available on supported platforms. Before use, pay attention to security configuration, especially when connecting other users or exposing the Gateway remotely.