- Services
A 678 KB AI assistant written in Zig that runs on $5 boards with about 1MB of RAM.
Teams that need the smallest possible agent for embedded hardware
Free and open source (MIT). You pay only for model usage.
A 678 KB binary with about 1MB peak memory and startup under 2 ms on Apple Silicon.
Pairing, allowlists, workspace limits, encrypted secrets and OS-level sandboxes.
SQLite with hybrid search by default, or PostgreSQL, Redis and other backends.
Import memory from an existing OpenClaw setup with a dry-run preview first.
Run an agent on a microcontroller-class board or a cheap single-board computer.
Run a Telegram or Slack assistant inside a strict sandbox.
Close alternatives worth a look before you decide.
A single Rust binary that runs a self-hosted AI assistant across 30+ channels.
A tiny AI assistant in Go that runs on $10 Linux boards with about 10MB of RAM.
The open source personal AI assistant that runs on your own hardware and answers in your chat apps.
NullClaw is an AI agent from NullClaw community. It runs as self-hosted and is offered under a open source model.
NullClaw is offered under a open source model. Model tokens are usually billed separately, so check the live model price on this page and the vendor site for current tiers.
The alternatives section on this page lists the closest options, with live data for each. Use the head-to-head pages to compare two of them in detail.
