GitHub topics

llamacpp

25% of these repos are in LLM Infrastructure.

Repositories

12

Total stars

61,736

Trending

janhq

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Created Aug 2023

Total45,890
30 days +960
llamastash

Zero-overhead, terminal-native local-LLM orchestrator. Run any engine, any model via the same proxy.

Created May 2026

ai gguf llamacpp llm lmstudio
Total303
30 days +77
intentee

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

Created Apr 2024

Total1,694
30 days +14
SilasMarvin

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

Created Nov 2023

ai auto-completion developer-tools ide language-client
Total3,217
30 days +13
floneum

Instant, controllable, local pre-trained AI models in Rust

Created May 2023

ai candle constrained-generation dioxus floneum-v3
Total2,236
30 days +11

Top

janhq

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Created Aug 2023

Total45,890
SilasMarvin

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

Created Nov 2023

ai auto-completion developer-tools ide language-client
Total3,217
floneum

Instant, controllable, local pre-trained AI models in Rust

Created May 2023

ai candle constrained-generation dioxus floneum-v3
Total2,236
intentee

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

Created Apr 2024

Total1,694
noumena-labs

AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider routing. Built with Rust & C++.

Created Mar 2026

Total125

Related

All topics →