macm1 b45d2e685a refactor: remove env vars persistence, only validate and export
Environment variables should NOT be saved to openclaw.json config.
Instead, they are injected directly into the gateway process via run.sh.

Flow:
  options.json (gateway_env_vars) → run.sh (export) → gateway process env

Changes:
- Remove cfg["env"] initialization from apply_gateway_settings
- Only validate env vars format and size limits in oc_config_helper.py
- Log validated vars but don't persist them to config
- run.sh remains responsible for parsing and exporting to process env
- Cleaner separation of concerns: helpers validates, run.sh exports
2026-02-23 06:00:01 +03:00
2026-02-22 20:00:43 +03:00

OpenClaw Assistant Home Assistant App/Add-on

Join our Discord Server!

OpenClaw Assistant

OpenClaw Home Assistant integration is available now! https://github.com/techartdev/OpenClawHomeAssistantIntegration

This repository contains a Home Assistant add-on that runs OpenClaw inside Home Assistant OS (HAOS).

Upstream rename history (FYI): clawdbot → moltbot → openclaw (final).

Key Features

  • AI Gateway — OpenClaw server with chat, skills, and automation capabilities
  • Web Terminal — browser-based terminal embedded in Home Assistant
  • Assist Pipeline — use OpenClaw as a conversation agent via the OpenAI-compatible API
  • Browser Automation — Chromium included for web scraping and automation skills
  • Proxy Support — optional outbound http_proxy setting for HTTP/HTTPS traffic
  • Persistent Storage — skills, config, and workspace survive add-on updates
  • Bundled Tools — git, vim, nano, bat, fd, ripgrep, curl, jq, python3, pnpm, Homebrew

Supported Architectures

Architecture Supported
amd64
aarch64 (RPi 4/5)
armv7 (RPi 3)

Documentation

Install

  1. Home Assistant → Settings → Add-ons → Add-on store
  2. ⋮ → Repositories
  3. Add this repo:
    • https://github.com/techartdev/OpenClawHomeAssistant
  4. Install OpenClaw Assistant

Star History

Star History Chart

Support / Donations

If you find this useful and you want to bring me a coffee to make more useful things, or support the project, use the link below:

S
Description
No description provided
Readme MIT 611 KiB
Languages
Shell 55.1%
Go Template 20.7%
Python 17.8%
Dockerfile 5.5%
JavaScript 0.9%