Find trending repositories by name or description.
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
SteelSeries headset manager for Linux — GG & Sonar alternative for Arctis: Sonar EQ with 330+ game presets, ChatMix, Game/Chat/Media mixer, spatial audio, sidetone, ANC, battery and OLED. Arctis Nova Pro Wireless & Wired, Nova Pro Omni, Nova Elite, Nova 7/7P/5/3, Arctis 7/7+/9/Pro Wireless, GameBuds. Built on PipeWire.
Sophon-Realtime v1: open full-duplex voice models that hear your tone and speak with one. Tag and Flash run on one GPU with vLLM-Omni; E2E in preview.
Open-source live-chat, email support, omni-channel desk. An alternative to Intercom, Zendesk, Salesforce Service Cloud etc. 🔥💬
Open Souce IM with AI powered live-chat, email, ticket support, omni-channel customer service，alternative to slack + zendesk/intercom/hubspot/ada/decagon/sierra
基于大语言模型的检索增强生成RAG示例
Self-hosted collection of powerful web-based tools for everyday tasks. No ads, no tracking, just fast, accessible utilities right from your browser!
Isaac Simulation MCP Extension and Server
An Omni Real-Time Assistant for Everyone
The open-source, self-hosted AI agent for your company. Works across workplace tools to find context, analyze information, and carry out tasks.
A framework for efficient model inference with omni-modality models
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
Omni inference in C/C++
We've moved to SGLang Omni Voxt: https://github.com/sgl-project/sglang-omni/tree/main/Voxt
Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an acting system, Cinema Studio 2.5/3.0/3.5, MCSLA, Soul ID consistency, Kling 3.0 Motion Control, the DISCIPLINE framework, and 18 templates.
The context layer for AI coding agents: less noise, fewer tokens, nothing lost. Formerly OMNI.
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Multimodal RL training framework for diffusion & omni models
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.
Omni Browser is a secure, open-source Android browser by RebelRoot. Built on Mozilla GeckoView, it features native WebExtension support, aggressive media stream interception, a private encrypted locker, and on-device machine learning tools.
Native macOS semantic search over your local files - text, images, audio, video in one vector space, on-device on Apple silicon.
集成 Agent、SDK 与 CLI 的微信读书增强工具包，内置 40 项操作。在覆盖官方功能的基础上，重磅支持阅读微信公众号，并全面解锁书架笔记读写、书籍导入与 AI 权限。
Open-source end-to-end omni interaction agent for natural full-duplex voice collaboration, continuous audio-visual perception, and asynchronous long-horizon agentic execution.
An open-source agent harness powered by the Qwen Omni Realtime API—see, hear, and act, with built-in memory.
OmniEdu: Open Foundation Models for Learning and Teaching