Keep Calm and Read the Friendly Manual :-)
Description:
Kagenti is a cloud-native middleware framework for deploying and orchestrating AI agents, with security, identity, and Kubernetes tooling. It provides lifecycle, networking, security, and observability components, enabling deployment of agents and tools via A2A and MCP protocols.
Description:
Omnigent is a meta-harness for AI agents that provides a common layer over Claude Code, Codex, Pi, and user-defined agents. It enables swapping harnesses, policy-driven governance, sandboxed execution, and real-time multi-user collaboration across sessions.
Description:
Odysseus is a self-hosted AI workspace that runs locally. It offers chat with local models, an agent that can use tools, a Cookbook for model discovery and serving, and memory-powered research and notes, all designed for privacy-first, offline-friendly operation.
Description:
Lemonade is an open-source local AI server that runs LLMs, speech, image, and other models on your own hardware. It provides OpenAI-compatible APIs, a Model Manager, and embeddable binaries for offline, private AI on CPU/GPU/NPUs.
Description:
Headroom is a library and proxy system that compresses texts, tool outputs, logs, and RAG chunks before they reach LLMs, achieving 60–95% reduction in tokens while preserving content. It includes a Python/TypeScript library, a drop-in proxy, and an MCP-based memory backend with reversible CCR compression.
Description:
GenCAD is an AI-driven parameterized CAD generator that creates CAD programs and 3D models from images, using transformer-based representations and diffusion priors to produce modifiable CAD commands.
Description:
MediaPipe is an open-source, cross-platform ML framework for building perception pipelines across mobile, web, desktop, and edge devices. It offers ready-to-use Solutions, models, and a modular framework to create efficient on-device ML pipelines.
Description:
RuView is a WiFi sensing platform that turns commodity WiFi CSI signals into real-time spatial intelligence, enabling presence detection, vital signs monitoring, pose estimation, and room mapping without cameras.
Description:
OmniVoice is a multilingual zero-shot TTS model with Python API and CLI for voice cloning and voice design across 600+ languages.
Description:
World Engine is a core library for World Model inference. It loads World Models and LoRA adapters to generate image frames from text and controller inputs, optimized across GPUs. It offers a simple API to load models and produce frames conditioned on prompts, history, and inputs.