NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Repository Index
104,105 visible repositories in the index
265–288 of 571 · Most stars
Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.
- tika-server
- python
- tika-python
- tika-server-jar
A fast, efficient universal vector embedding utility package.
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
- agent
- agent-framework
- python
- framework
MonkeyOCRv2 Vision Encoder — A Document-Native Visual Backbone
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
A cross-platform Flutter app that runs uncensored, 100% offline open-source AI models (GGUF) directly on your Android, iOS, or PC. No cloud, no filters, total privacy.
- flutter
- local-ai
- uncensored-ai
WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.
One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.
Run Claude Code from a USB drive on any PC — no installation required.
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
- ai
- assistant-chat-bots
- computer-vision
- llm
Measuring Massive Multitask Language Understanding | ICLR 2021
- muti-task
- transfer-learning
- gpt-3
- few-shot-learning
Build AI agents for your PC
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
- deepseek
- inference
- inference-engine
- llm-inference
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
- ai
- huggingface
- language-model
- transformer
🤖 Deploy a private ChatGPT alternative hosted within your VPC. 🔮 Connect it to your organization's knowledge base and use it as a corporate oracle. Supports open-source LLMs like Llama 2, Falcon, and GPT4All.
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
Build and iterate on your UI 10x faster with AI - right from your own IDE ☕️
[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
Chat with your favourite LLaMA models in a native macOS app
Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM
StockBot powered by Groq: Lightning Fast AI Chatbot that Responds With Live Interactive Stock Charts, Financials, News, Screeners, and More. Powered by Llama3-70b on Groq, Vercel AI SDK, and TradingView Widgets.