OpenClaw
OpenClaw is a personal AI assistant that runs on your own devices. It supports multiple messaging channels including WhatsApp, Telegram, Slack, Discord, Signal, iMessage, IRC, Microsoft Teams, Matrix, and more. Features voice wake mode, live canvas, browser control, skills platform, and a Gateway WebSocket control plane.
Install
bash -c "$(curl -fsSL https://raw.githubusercontent.com/Heretek-AI/ProxmoxVE/main/ct/openclaw.sh)"Run as root in the Proxmox VE shell. Pick Default for the sizing below, or Advanced to choose storage, network and resources yourself.
Notes
- Warning: HTTPS uses self-signed certificate - click 'Advanced' -> 'Proceed to site' in browser
- Warning: CRITICAL: A model provider MUST be configured after installation (Ollama, OpenAI, Anthropic, etc.)
- Warning: Memory search requires embedding provider (Ollama, OpenAI, Gemini, Voyage, or local model)
- Warning: The openclaw user has no login shell - use full path '/home/openclaw/.npm-global/bin/openclaw' or 'export PATH=/home/openclaw/.npm-global/bin:$PATH' to run commands
- Access the Gateway at http://<IP>:18789
- HTTPS Access (secure): https://<IP>:18790
- WebSocket endpoint: ws://<IP>:18789 (or wss://<IP>:18790 for secure)
- Requires Node.js 24 (installed automatically)
- Configuration stored in /home/openclaw/.openclaw/
- For remote LAN access, use HTTPS (port 18790) or SSH tunnel: ssh -L 18789:localhost:18789 root@<container-ip>
- To configure a model provider: /home/openclaw/.npm-global/bin/openclaw models auth add --provider <provider>
- For local/offline use: Install Ollama and run 'ollama pull llama3.2' then 'ollama pull nomic-embed-text'
- To configure channels (Telegram, Discord, WhatsApp, etc.): /home/openclaw/.npm-global/bin/openclaw channels add --channel <name>
- Verify installation: /home/openclaw/.npm-global/bin/openclaw doctor && /home/openclaw/.npm-global/bin/openclaw gateway status
- View logs: journalctl -u openclaw-gateway -f
- Auth token saved to /home/openclaw/.openclaw/auth_token - view with: cat /home/openclaw/.openclaw/auth_token
- Service management: systemctl start/stop/restart/status openclaw-gateway
- View logs: journalctl -u openclaw-gateway -f
Script details
You might also need
Hermes Agent
LXCAI / Coding & Dev-Tools · debian 13
Hermes Agent is a self-improving AI agent built by Nous Research with persistent memory, autonomous skill creation, computer-use (CUA) support, and multi-platform gateway integration. This enhanced Heretek build includes pre-configured passwordless sudo for the hermes user, native X11/input shared libraries for cua-driver, and Docker Engine with Buildx and Compose v2.
Kyojin
LXCAI / Coding & Dev-Tools · ubuntu 24.04
Kyojin is Yamz Labs' open source inference engine for AMD Strix Halo (gfx1151), built on ExLlamaV3 with speculative decoding, serving their own EXL3 quantised builds of Qwen3.8-Flash-Next, GLM-5.3-Flash and MiMo-V2.6-Flash (95 to 106 GB) on one 128 GB machine through an OpenAI-compatible API. The script builds the latest tagged release with AMD's gfx1151 ROCm wheels, following Kyojin's own container recipe.
GSQHalo.cpp
LXCAI / Coding & Dev-Tools · debian 13
GSQHalo.cpp is a llama.cpp fork tuned for ISTA-DASLab's GSQ-RCO quantizations of Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151), with faster prefill kernels, MTP that fits in memory and a KV cache on SSD. The script installs AMD's ROCm 7.14.1 for gfx1151 in its own prefix, builds the fork from source and serves llama-server's OpenAI-compatible API.
Gufo
LXCAI / Coding & Dev-Tools · debian 13
Gufo is an open source local inference engine built and tuned for AMD Strix Halo (Ryzen AI MAX+ 395, Radeon 8060S gfx1151). It serves Qwen3.8, DeepSeek V4 Flash, speech, embedding, image and video models through an OpenAI-compatible API, with speculative decoding, concurrent requests and prompt caching. The script installs the official release build through Nix, using prebuilt ROCm from the Gufo binary cache.