Lemon AI
A self-hosted AI agent for research, coding and data analysis, with Ollama or vLLM support, Docker code execution and an HTML editor.

Lemon AI is a local AI agent for people who want to research topics, write code and analyze data on their own hardware. It also lets you revise generated HTML reports and pages without asking the agent to recreate the whole result.
- Research and document work: The agent can search the web, browse pages, process documents and produce research reports or other content.
- Code and data analysis: It generates and executes code inside a local Docker-based sandbox that isolates execution from the host's files and operating system.
- HTML editing: You can ask the agent to change a selected section, add content or adjust formatting, and edit text directly for smaller corrections.
- Conversation memory: The agent keeps memories from conversations and an experience repository for reusing previous work and adapting to business needs.
Local models run through Ollama or vLLM, including DeepSeek, Kimi, Qwen, Llama, Gemma and GPTOSS. Local model execution doesn't require a cloud model service, but web research still uses online resources. Optional Claude, GPT, Gemini and Grok API connections send requests to those providers.
Lemon AI supports macOS and Linux, plus Windows through WSL. The local setup uses Docker Desktop, and the application recommends a modern processor and at least 4 GB of RAM. Client and container deployments are available alongside a hosted subscription offering.