Run Lemon AI Locally – Open-Source General AI Agent Like Manus & Genspark AI! (Patreon)
Content
Video: https://youtu.be/W6R8Ux0sDsU
In this video, you’ll learn how to run Lemon AI—a full-stack, open-source, general AI agent —entirely on your local machine using Docker and WSL2 on Windows. We walk through the complete setup process, from installing Ubuntu via WSL2 and configuring Docker Desktop to integrating local language models like Qwen3 Coder via Ollama, and even connecting cloud-based models through OpenRouter. You’ll see Lemon AI in action: autonomously planning multi-step tasks, generating marketing websites, creating AI video storylines, and adapting to your feedback mid-process. This tutorial is ideal for developers, AI enthusiasts, content creators, and tech-savvy professionals who want to explore agentic AI without relying on cloud subscriptions. Understanding and running general AI agents locally matters because it gives you full control, privacy, and the ability to customize intelligent automation for your own workflows—today, not years from now.
Lemon AI is the first Full-stack Open-source Self-Evolving General AI Agent
https://lemonai.ai/
GitHub:
https://github.com/hexdocom/lemonai
Installation
Enter in WSL and execute the pull Lemon AI sandbox command
1 :
docker pull hexdolemonai/lemon-runtime-sandbox:latest
2 :
docker run -it --rm --pull=always \
--name lemon-app \
--env DOCKER_HOST_ADDR=host.docker.internal \
--env ACTUAL_HOST_WORKSPACE_PATH=${WORKSPACE_BASE:-$PWD/workspace} \
--publish 5005:5005 \
--add-host host.docker.internal:host-gateway \
--volume /var/run/docker.sock:/var/run/docker.sock \
--volume ~/.cache:/.cache \
--volume ${WORKSPACE_BASE:-$PWD/workspace}:/workspace \
--volume ${WORKSPACE_BASE:-$PWD/data}:/app/data \
--interactive \
--tty \
hexdolemonai/lemon:latest make run