- Services
A single Rust binary that runs a self-hosted AI assistant across 30+ channels.
Running an always-on assistant on small servers or edge hardware
Free and open source (MIT or Apache 2.0). You pay only for model usage.
Install one file and register it as a background service on Linux, macOS or Windows.
Workspace limits, command policies, OS sandboxes and signed receipts for every tool call.
Route between Anthropic, OpenAI, Ollama and other providers, with fallback when one fails.
Trigger standard procedures from webhooks, schedules or devices, with approval gates.
Run a personal assistant on a small server that answers in Telegram or Discord.
Let an agent read sensors and control devices on embedded boards.
Run routine operations jobs where risky steps wait for a human to approve.
Close alternatives worth a look before you decide.
A tiny AI assistant in Go that runs on $10 Linux boards with about 10MB of RAM.
A 678 KB AI assistant written in Zig that runs on $5 boards with about 1MB of RAM.
The open source personal AI assistant that runs on your own hardware and answers in your chat apps.
An ultra-lightweight, self-hosted personal AI agent in Python with a web UI, memory and chat apps.
ZeroClaw is an AI agent from ZeroClaw Labs. It runs as self-hosted and is offered under a open source model.
ZeroClaw 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.
