Nectar is a powerful, Local AI-Inferencing application that allows the user download create and run agents and run large language models on your own machine.

With no internet connection required, Nectar ensures privacy-first, high-performance inference using cutting-edge open-source models from Hugging Face, Ollama, and beyond.

Whether you’re generating natural language, analyzing text, or embedding AI into your workflows, Nectar gives you full control over how and where your models run—optimized for efficiency and user freedom. it gives users the ability to building agents, connecting knowledge, and performing deep research.

• 🔒 Offline Inference – Run LLMs locally with zero cloud dependency.
• ⚡ Fast & Lightweight – Real-time performance on consumer hardware.
• 🧩 Model Flexibility – Supports GGUF, GPTQ, and other formats with Hugging Face & Ollama integration.
• 🖥️ Developer Ready – Use Nectar as your intelligent backend for automation, coding, content creation, or research.
• 🛠️ Built on Zashirion AI Engine – With an intuitive UI and powerful API layer for embedding into custom workflows.
• 🤖 Custom Agents – Build AI agents with unique instructions, knowledge, and actions.
• 🌍 Web Search – Integrates Google, duckduckgo, and microsoft edge scrapers.
• 🔍 RAG (Retrieval-Augmented Generation) – Hybrid search + knowledge graph for uploaded files & connected data sources.
• 🔬 Deep Research – Multi-step, agentic search for in-depth answers.
• ▶️ Actions & MCP – Allow AI agents to interact with external systems.
• 💻 Code Interpreter – Execute Python for data analysis, graphing, and file generation.
• 🎨 Image Generation – Create images from user prompts.
• 👥 Collaboration Tools – Chat sharing, feedback, user management, usage analytics, and more.
• ✅ Ideal for: developers, researchers, cybersecurity experts, and power users who want AI without sacrificing privacy or control.

Nectar-X-Studio works with all LLM Models (OpenAI's GPT, Mistral, meta's llama, etc.) and self-hosted models (Ollama, vLLM, etc.).

  pip install "llama-cpp-python==0.3.4" --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121

  pip install "llama-cpp-python==0.3.4" --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/rocm6.0

  pip install llama-cpp-python==0.3.4