Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

Implementation of Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework

BlenderLLM: A LLM specifically designed to generate CAD scripts based on user instructions. These scripts are then executed in Blender to render 3D models.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

A secure chat app that connects with Deepseek:r1 or other open source models, featuring real-time updates and memory-like chatgpt with no external dependencies.

TalkNexus: Ollama Chatbot Multi-Model & RAG Interface

Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

A Web-app for OpenManus

Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves

⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡️, supports…

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

PocketFlow's node-based workflow structure, with Manus' agents and tools!

No fortress, purely open ground. OpenManus is Coming.

A python package for developing AI applications with local LLMs.

An example of using multimodal LLMs to processpide feed from camera and get image description

[CVPR 2025]Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

MultiModal Rag with Colpali, Milvus and VLM

Local llamaindex RAG to assist researchers quickly navigate research papers

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Multimodal AI agent with Llama 3.2: A Streamlit app that processes text, images, PDFs, and PPTs, integrating NIM microservices, Milvus, and Llama-3.2 models.

Fast and memory-efficient exact attention

Serving LLMs in the HF-Transformers format via a PyFlask API