Tool profile
Lumabri
github.com
Pure-C private inference service that runs large AI models across your own computers and servers.
What it does
Lumabri
Lumabri (Apache-2.0) runs a private inference service across your computers, powered by the Colibri engine. You choose models, select which computers on your LAN may help and approve how their memory is used; a worker loads only the weights for its assigned layers, so models that do not fit on one machine can be shared. Chat from the terminal UI or a bundled web page. The controller, TUI and inference integration are written in C. The README notes that extra computers add usable memory and capacity but do not guarantee more tokens per second.
Tags
Categories
A concise summary has not been added yet.
FAQ
Frequently asked questions
- What is Lumabri?
- Lumabri (Apache-2.0) runs a private inference service across your computers, powered by the Colibri engine. You choose models, select which computers on your LAN may help and approve how their memory is used; a worker loads only the weights for its assigned layers, so models that do not fit on one machine can be shared. Chat from the terminal UI or a bundled web page. The controller, TUI and inference integration are written in C. The README notes that extra computers add usable memory and capacity but do not guarantee more tokens per second.
- How much does Lumabri cost?
- Lumabri uses a Open source pricing model. Check the official website for current plans.
- What is Lumabri used for?
- Lumabri is listed on TolsAI under: AI Developer Tools and Large Language Models (LLMs).
- Where can I use Lumabri?
- Lumabri is available on its official website, github.com.
Explore
More in AI Developer Tools
you.bot: The same AI models for up to 46% less. you.bot is one API for 70+ LLM, image, video and music models — Claude, GPT, Gemini, Kling, Seedance, Veo, GPT Image 2, Nano Banana Pro, Suno and more —
Corrath: Corrath is an AI security gateway for modern AI applications. It sits between your app and AI providers to protect API keys, block prompt injections, control spending, monitor usage, detect t
Turn a codebase plus its docs, SQL schemas, configs and PDFs into a queryable knowledge graph for coding agents.
A coding-agent skill from Cloudflare for multi-phase security audits with verified, machine-readable findings.
High-throughput, memory-efficient inference and serving engine for LLMs.
Redis/Valkey-compatible in-memory database in Rust with built-in full-text and vector search.
Discussion
Discussion
Log in to join the discussion
No comments yet. Start the discussion.