Explore live open-source projects and AI models.

offline text to speech and free SOTA LLM APIs to let your programs speak to you

🚀 A powerful Flutter-based AI chat application that lets you run LLMs directly on your mobile device or connect to local model servers. Features offline model execution, Ollama/LLMStudio integration, and a beautiful modern UI. Privacy-focused, cross-platform, and fully open source.

Designed for offline use, this RAG application template offers a starting point for building your own local RAG pipeline, independent of online APIs and cloud-based LLM services like OpenAI.

Wuhe Design presents the Krita × Ollama Prompt Generator — a local LLM-powered plugin for generating, refining, and sending prompts directly into the krita-ai-diffusion Stable Diffusion plugin. Supports Gemma models, voice input, bilingual output, and fully offline workflow.

Personalized Bluesky moderation making use of labelers and online/offline LLMs

[ICML 2026] BizFinBench.v2: A Unified Offline–Online Bilingual Benchmark for Expert-Level Financial Capability Evaluation of LLMs

an offline conversational AI assistant integrating Whisper (speech-to-text), Llama 3.2 (LLM), and Piper (text-to-speech) with persistent memory management. System runs entirely locally without cloud dependencies.

Pipeline LLMs offline combine with own context for generating answer

Live2D + ASR + LLM + TTS → Real-time communication + Offline Deployment/Cloud Inference 实时沟通 本地部署/云端推理

Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and Adaptive Quantization"