Search Results for "energy"
Sort By:
Showing 33 open source projects for "energy"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
OpenJarvis
Personal AI, On Personal Devices
...Developed as part of the Intelligence Per Watt research initiative, it focuses on improving the efficiency and practicality of on-device AI systems. The framework provides shared primitives for building local-first agents, along with evaluation tools that measure performance using metrics such as energy consumption, latency, cost, and accuracy. OpenJarvis integrates with local inference engines like Ollama, vLLM, SGLang, and llama.cpp to run language models directly on personal hardware. It also includes a learning loop that allows models to improve over time using locally generated interaction traces. By prioritizing local execution and efficiency, OpenJarvis aims to provide a foundation for privacy-preserving personal AI assistants. -
2
Materials Discovery: GNoME
AI discovers 520000 stable inorganic crystal structures for research
...The project centers on Graph Networks for Materials Exploration (GNoME), a message-passing neural network architecture trained on density functional theory (DFT) data to predict material stability and energy formation. Using GNoME, DeepMind identified 381,000 new stable materials, later expanding the dataset to include over 520,000 materials within 1 meV/atom of the convex hull as of August 2024. The repository provides datasets, model definitions, and interactive Colabs for exploring these materials, computing decomposition energies, and visualizing chemical families. ... -
3
bitnet.cpp
Official inference framework for 1-bit LLMs
...At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous compute infrastructure. The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. BitNet is built to scale across architectures, with configurable kernels and tiling strategies that adapt to different hardware, and it supports large models with impressive throughput even on modest resources. -
4
ESP32 iPhone Agent
Let an AI model use a real iPhone with a $7 ESP32
...Compatible vision models interpret screenshots and generate actions such as taps, swipes, typing, and navigation. The microcontroller executes these actions through USB mouse and keyboard interfaces using iOS AssistiveTouch. Bluetooth Low Energy connects the application with the hardware controller. The system operates without jailbreaking, a Mac, or an Apple developer account. It supports OpenAI-compatible vision models for automated mobile workflows. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
AutoClip
AI-powered video clipping and highlight generation
...The system supports downloading videos from major platforms (e.g. YouTube, Bilibili), or accepting local uploads, and then applies AI analysis to identify segments worth clipping based on content (e.g. high energy moments, speech, or other heuristics). Once highlights are identified, AutoClip can automatically cut those segments and optionally assemble them into a compilation, thus greatly reducing manual video editing effort. It uses a modern web application stack with a front end (React + TypeScript) for user interaction and a back end that handles downloading, processing, clipping, and queue management, allowing real-time progress feedback and easy deployment, e.g. via Docker. -
6
Bear Stone Smart Home
Custom Home Assistant configuration with automations and scripts setup
...It demonstrates how to structure Home Assistant YAML files for scalability and maintainability in a real-world deployment. Bear Stone Smart Home also showcases custom automations and scripts designed to improve convenience, energy efficiency, and overall smart home behavior. Additionally, it may include examples of dashboards and user interface customization to enhance usability and visualization of home data. Overall, it serves as a practical reference for building and refining a tailored Home Assistant setup. -
7
SpeechRecognition
Speech recognition module for Python
...Recognize speech input from the microphone, transcribe an audio file, save audio data to an audio file. Show extended recognition results, calibrate the recognizer energy threshold for ambient noise levels (see recognizer_instance.energy_threshold for details). Listening to a microphone in the background, various other useful recognizer features. The easiest way to install this is using pip install SpeechRecognition. The first software requirement is Python 2.6, 2.7, or Python 3.3+. This is required to use the library. ... -
8
SpikingJelly
SpikingJelly is an open-source deep learning framework
...The project provides the components needed to build, train, and evaluate neural models that communicate through discrete spikes rather than the continuous activations used in conventional artificial neural networks. This makes it especially relevant for researchers interested in biologically inspired computing, event-driven processing, and energy-efficient AI systems. The framework includes neuron models, surrogate gradient training methods, encoding strategies, network components, and utilities for simulation and experimentation, allowing users to develop a wide variety of spiking architectures. It also supports integration with familiar PyTorch workflows, which lowers the barrier for machine learning practitioners who want to explore spiking approaches without abandoning mainstream tooling. -
9
Tokscale
A CLI tool for tracking token usage from OpenCode, Claude Code
Tokscale is a CLI and terminal UI tool that tracks token usage and estimated cost across multiple AI coding assistants and development workflows. It treats tokens like a measurable resource, helping developers understand how much “AI energy” they are consuming over time and where it is being spent. The tool aggregates usage across supported platforms and presents it through interactive views that let users filter, sort, and explore trends without leaving the terminal. Tokscale also includes rich visualizations such as contribution-graph style summaries and daily breakdowns, making it easy to spot spikes, habits, and long-term patterns. ... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
hls4ml
Machine learning on FPGAs using HLS
...This approach allows machine learning algorithms to run directly on specialized hardware, making them suitable for applications that require extremely fast response times and minimal power consumption. The framework was originally developed for high-energy physics experiments where real-time decision systems must process large volumes of data with strict latency constraints. Over time, it has expanded to support a variety of scientific and industrial applications including signal processing, embedded systems, and biomedical monitoring. -
11
IVY
The Unified Machine Learning Framework
...Choose the most appropriate device or combination of devices for your needs. DeepMind releases an awesome model on GitHub, written in JAX. We'll use PerceiverIO as an example. Implement the model in PyTorch yourself, spending time and energy ensuring every detail is correct. Otherwise, wait for a PyTorch version to appear on GitHub, among the many re-implementation attempts that appear (a, b, c, d, e, f). Instantly transpile the JAX model to PyTorch. This creates an identical PyTorch equivalent of the original model. -
12
PyTorch Geometric Temporal
Spatiotemporal Signal Processing with Neural Machine Learning Models
...Moreover, it comes with an easy-to-use dataset loader, train-test splitter and temporal snaphot iterator for dynamic and temporal graphs. The framework naturally provides GPU support. It also comes with a number of benchmark datasets from the epidemiological forecasting, sharing economy, energy production and web traffic management domains. Finally, you can also create your own datasets. The package interfaces well with Pytorch Lightning which allows training on CPUs, single and multiple GPUs out-of-the-box. PyTorch Geometric Temporal makes implementing Dynamic and Temporal Graph Neural Networks quite easy - see the accompanying tutorial. ... -
13
Uranie
Uranie is CEA's uncertainty analysis platform, based on ROOT
Uranie is a sensitivity and uncertainty analysis plateform based on the ROOT framework (http://root.cern.ch) . It is developed at CEA, the French Atomic Energy Commission (http://www.cea.fr). It provides various tools for: - data analysis - sampling - statistical modeling - optimisation - sensitivity analysis - uncertainty analysis - running code on high performance computers - etc. Thanks to ROOT, it is easily scriptable in CINT (c++ like syntax) and Python. Is is available both for Unix and Windows platforms (a dedicated platform archive is available on request). ... -
14
MARS5
MARS5 speech model (TTS) from CAMB.AI
...It uses a two-stage architecture that combines an autoregressive (AR) model with a non-autoregressive (NAR) model, giving it both expressiveness and speed. The model is built to handle prosodically challenging content such as sports commentary, anime dialogue, and other high-energy or highly varied speech patterns with realistic rhythm and intonation. To control speaker identity, MARS5 uses a short reference audio clip, typically between 2 and 12 seconds, from which it learns the voice characteristics. It supports two main inference modes: shallow clone, which is faster and only needs the reference audio, and deep clone, which additionally uses the transcript of the reference audio to increase similarity and naturalness at the cost of more computation. -
15
EmotiVoice
Multi-Voice and Prompt-Controlled TTS Engine
...The core idea is prompt-based emotional and style control: you can ask the engine to speak “happy,” “sad,” “excited,” or with other high-level style prompts that shape prosody, pitch, speed, and energy. EmotiVoice provides multiple ways to interact with it, including a web interface, a Docker image, an HTTP API (including an OpenAI-compatible TTS API), and Python scripts for batch synthesis. It also supports voice cloning with your own data, backed by recipes for popular datasets like DataBaker and LJSpeech, so you can train or adapt voices to custom personas. -
16
PaddlePaddle models
Pre-trained and Reproduced Deep Learning Models
...The model library of Flying Paddle is an industrial-level model library tailored around the actual R&D process of domestic enterprises, serving enterprises in many fields such as energy, finance, industry, and agriculture. -
17
Text2Video
Software tool that converts text to video for more engaging experience
...I started this project because during this semester, I have been given many reading assignments and I felt frustration in reading long text. For me, it was very time and energy-consuming to learn something through reading. So I imagined, "What if there was a tool that turns text into something more engaging such as a video, wouldn't it improve my learning experience?" I created a prototype web application that takes text as an input and generates a video as an output. I plan to further work on the project targeting young college students who are aged between 18 to 23 because they tend to prefer learning through videos over books based on the survey I found. ... -
18
EECluster
Tool for energy-efficient resource management in HPC clusters
EECluster is software tool for managing the energy-efficient allocation of the cluster resources. EECluster uses a Hybrid Genetic Fuzzy System as the decision-making mechanism that elicits part of its rule base dependent on the cluster workload scenario, delivering good compliance with the administrator preferences. In the latest version, we leverage a more sophisticated and exhaustive model that covers a wider range of environmental aspects and balances service quality and power consumption with all indirect costs, including hardware failures and subsequent replacements, measured in both monetary units and carbon emissions. ... -
19
Portable Robotics Eye Vergence Control
Eye movements control portable on different robotic stereo heads
...The project is now available for the iCub platform to work on YARP [https://github.com/stino78/vergence-control/][1] The algorithm works on the top of a distributed representation of binocular disparity supplied by a population of binocular energy-model neural units. The project allows a robust control and adaptive binocular coordination for different robot stereo platforms. Reference publications: Gibaldi, A., Vanegas, M., Canessa, A., & Sabatini, S. P. (2017). A portable bio-inspired architecture for efficient robotic vergence control. International Journal of Computer Vision,. ... -
20
EVLib
Management and simulation of Electric Vehicles activities
...EVLib provides a simple, yet efficient interface for the management of all major EV related activities such as the charging and dis-charging of batteries, as well as battery swapping. Moreover, a large number of parameters, such as the number of chargers, the waiting queues, and the available energy can be easily con figured. On top of this, the library supports the simultaneous operation of many EV activities through the efficient use of threads. -
21
Low-power approximate adders provide basic building blocks for approximate computing hardware that have shown remarkable energy efficiency for error-resilient applications (like image/video processing, computer vision, etc.), especially for battery-driven portable systems. In this paper, we present a novel scalable, fast yet accurate analytical method to evaluate the output error probability of multi-bit low power adders for a predetermined probability of input bits.
-
22
ProtPOS
Prediction of PROTtein Preferred Orientation on a Surface
ProtPOS is a self-contained, lightweight, and easy-to-use software package for predicting the preferred orientation of protein on a given surface upon initial adsorption. It searches quickly for the low energy protein poses in all translational and rotational degrees of freedom of the protein with respect to the surface using particle swarm optimization. Each successful run returns the lowest energy orientation of the protein on the surface in PDB format, which is readily used for MD simulations. ProtPOS is implemented in Python, making use of the PyMOL library for generating protein conformations and calling GROMACS externally to calculate protein-surface interaction energies. ... -
23
bnns
Research tool for interactive training of artificial neural networks.
BNNS is a research tool for interactive training of artificial neural networks based on the Response Function Plots visualization method. It enables users to simulate, visualize and interact in the learning process of a Multi-Layer Perceptron on tasks which have a 2D character. Tasks like the famous two-spirals task or classification of satellite image data. -
24
An open-source C++ library of machine learning by New York University's machine learning lab, led by Yann LeCun. In particular, implementations of convolutional neural networks with energy-based models along with a GUI, demos and tutorials.
-
25
april
Simulating worlds in a computer
The April project defines a set of C++ objects (World, Actor, Sensor, Reflex, Brain, Actuator, Event) that help simulate various environments. The world has an amount of energy that the user may use to create Actors and components while Actors may also create other Actors from their own energy. The code is structured in several layers: - april-core simply defines the library and the objects - april-gui builds on the concepts in april-core, giving a visual interpretation to the concepts - AprilDream is a GUI program that uses april-gui objects to display a World in evolution. ...
