This is a fully functional CPU-only setup guide for Gensyn CodeAssist,
tested on Ubuntu 22.04 VPS instances with zero GPU dependencies.
CodeAssist is an AI coding assistant that trains on your local workflow —
learning your reasoning style and evolving through interaction.
sudo apt update -y && sudo apt upgrade -y
sudo apt install -y git python3 python3-venv python3-pip curl ca-certificates gnupg lsb-releaseRemove any old installations:
sudo apt remove -y containerd containerd.io docker docker.io docker-ce docker-ce-cli || trueAdd the official Docker repository:
sudo mkdir -p /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/nullInstall Docker:
sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
sudo systemctl enable docker
sudo systemctl start docker
sudo docker run hello-worldsudo usermod -aG docker $USER
newgrp dockerIf you previously had Docker containers or ran an old CodeAssist instance:
sudo systemctl stop docker
sudo rm -rf /var/lib/docker
sudo systemctl start dockergit clone https://github.com/gensyn-ai/codeassist.git
cd codeassist
python3 -m venv .venv
source .venv/bin/activate
pip install -U pip uv
uv sync || pip install -r requirements.txtGenerate a token at 👉 https://huggingface.co/settings/tokens
→ Select “Write” permission.
Then export your credentials:
export HF_TOKEN="your_huggingface_token"
export HF_USER="your_huggingface_username"(Optional — make it permanent):
echo 'export HF_TOKEN="your_huggingface_token"' >> ~/.bashrc
echo 'export HF_USER="your_huggingface_username"' >> ~/.bashrcMake sure port 3000 isn’t locked:
sudo ss -ltnp | grep 3000 && echo "⚠️ Port 3000 occupied"
sudo kill -9 $(sudo ss -ltnp | grep 3000 | awk '{print $NF}' | sed 's/.*pid=//;s/,.*//') 2>/dev/null || true
sudo systemctl restart dockerIf it still shows ⚠️ Port 3000 occupied, run manually:
sudo kill -9 2324546
sudo ss -ltnp | grep 3000 || echo "✅ Port 3000 now free"
sudo systemctl restart dockercd ~/codeassist
source .venv/bin/activate
uv run run.pyWait for:
CodeAssist started at http://localhost:3000
If running on a remote VPS, forward the ports with SSH:
ssh -L 3000:localhost:3000 -L 8000:localhost:8000 -L 8001:localhost:8001 ubuntu@<your-vps-ip>Then open: 👉 http://localhost:3000
Created by @0xAkey
Made by @0xAkey on X 💫
Based on the official Gensyn CodeAssist repository.
This version focuses on CPU VPS deployment and HuggingFace-linked operation.
