LLaMA-Omni vs caveman

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

LLaMA-Omnicaveman
TaglineLLaMA-Omni is a speech interaction model built upon Llama-3.1-8B-Instruct, allowing for seamless low-latency speech-to-speech and speech-to-text interactions.Cuts 65% of tokens in AI coding agent responses.
Stars3.1k86k
Forks2234.8k
Open issues52370
LanguagePythonJavaScript
LicenseApache-2.0MIT
Last pushedMay 19, 2025Jul 3, 2026
CategoriesSpeech & AudioDeveloper Tools, LLM Frameworks

LLaMA-Omni

This repository contains the source code for LLaMA-Omni, an innovative end-to-end speech interaction system that generates both text and speech responses based on speech inputs, with a latency as low as 226ms. It features advanced training techniques and is available in varying parameter sizes.

Python

caveman

A skill/plugin for various AI agents, including Claude Code and other platforms, reducing output tokens for more concise, direct communication while maintaining accuracy.

JavaScript