Bino5150 /
lumina
Local-first desktop AI agent with memory, voice, and coding tools for modest GPUs
- 185 stars
- 4 stars since 3 Oct
- Python
- Updated today
- Some experience
- AI agents
Lumina is a desktop AI agent that runs on your own computer. It was built and tested on a 4GB Nvidia Quadro T1000, so the author kept prompts and tool definitions lean for small local models. The README argues that many assistants waste context on bloated prompts, and Lumina tries to avoid that.
It has a native PySide6/Qt interface instead of an Electron shell. Behind the chat window is one shared interface for 14 model backends. These include llama.cpp, Ollama, LM Studio and vLLM locally, plus cloud options like Anthropic, Google and OpenAI. You can switch backends from a Settings dropdown without a restart.
Memory and safety get a lot of attention. Memory is split into several parts: a decaying layered store, chat history search, a knowledge base and a step called Dreaming. Sessions are marked as owner or non-owner. Non-owner sessions start with all tools off, and outside content is treated as data, not instructions. The README is candid that you need a GPU and some comfort with a terminal. It is also in public beta, and macOS and Windows support is still being tested.
What it does
Layered persistent memory
Includes a decaying hierarchy called MemPalace, full-text chat history search, a knowledge base, Dreaming, and one-click memory backup.
14 swappable LLM backends
Local engines, a self-hosted gateway, and native or OpenAI-compatible cloud providers share one interface. Each keeps its own context window settings.
Software-engineering tools
Git inspection, managed worktrees, structured test runs with real pass/fail results, coding checkpoints and a diff-review view.
Voice, vision and images
Local Whisper speech input, text-to-speech with Kokoro or voice cloning, image input, and image generation that needs an estimate-then-confirm step before spending.
Personas and remote access
Personas are JSON files with their own prompt and voice. You can reach the agent through Telegram (full trust) or Discord (sandboxed).
What you could build
- Run a private assistant on a laptop GPU with llama.cpp or Ollama.
- Hand a coding task to an agent that edits files, runs tests and shows a diff for review.
- Build a custom persona with its own system prompt and cloned voice.
- Compare local and cloud models by switching backends in the same chat.
- Message your agent from your phone through Telegram while it runs at home.
Get started
The README excerpt gives no install commands, so start with the full manual in the repo's docs/ folder. You will need a local model backend such as llama.cpp installed first.
Commands are copied from the project's README. Read it on GitHub for the full setup.
More in AI agents
openclaw
Self-hosted AI assistant that answers in your chat apps and runs on your own machine
hermes-agent
Self-hosted AI agent that keeps skills and memory, and chats via terminal or Telegram
TradingAgents
A team of LLM agents that debate and decide on stock trades, for research
paperclip
A Node.js server and React dashboard for running a team of AI agents like a company
autoresearch
Let an AI agent edit a small LLM training script overnight and keep what improves it
ruflo
Agent harness adding swarms, memory and plugins around Claude Code and Codex
OpenManus
Open-source general AI agent that runs tasks from your terminal with your own LLM key
multica
A shared board where you assign issues to AI coding agents like teammates
openhuman
Rust agent harness with a desktop app, terminal client and embeddable library
buzz
Self-hostable team workspace where people and AI agents share channels on a Nostr relay