Search Results for "interface" - Page 97
Sort By:
Showing 16669 open source projects for "interface"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Pixeltable
Data Infrastructure providing an approach to multimodal AI workloads
Pixeltable is an open-source Python data infrastructure framework designed to support the development of multimodal AI applications. The system provides a declarative interface for managing the entire lifecycle of AI data pipelines, including storage, transformation, indexing, retrieval, and orchestration of datasets. Unlike traditional architectures that require multiple tools such as databases, vector stores, and workflow orchestrators, Pixeltable unifies these functions within a table-based abstraction. ... -
2
Cradle framework
The Cradle framework is a first attempt at General Computer Control
...The system introduces the concept of General Computer Control, where AI agents receive screenshots as input and perform actions through simulated keyboard and mouse operations. This approach allows agents to interact with any software interface without relying on specialized APIs or predefined automation scripts. The framework integrates reasoning, planning, and memory modules that help the agent understand its environment and execute long sequences of actions. Cradle agents are capable of performing tasks across a wide variety of environments, including computer applications and video games, demonstrating the generality of the approach. ... -
3
Chat with LLMs Everywhere
Run PyTorch LLMs locally on servers, desktop and mobile
TorchChat is an open-source project from the PyTorch ecosystem designed to demonstrate how large language models can be executed efficiently across different computing environments. The project provides a compact codebase that illustrates how to run conversational AI systems using PyTorch models on laptops, servers, and mobile devices. It is intended primarily as a reference implementation that shows developers how to integrate large language models into applications without requiring a... -
4
Reader LLM
Convert any URL to an LLM-friendly input with a simple prefix
Reader LLM is an open-source tool designed to convert web content into formats that are easier for large language models to process. The system works by transforming a webpage into a clean text or Markdown representation that removes unnecessary formatting and highlights the core information within the page. Developers can use a simple URL prefix to retrieve a version of a webpage that has been optimized for machine consumption, making it suitable for use in AI agents or retrieval-augmented... -
$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.
-
5
MemFree
Hybrid AI Search Engine & AI Page Generator
memfree is an open source hybrid AI search engine and page generation platform designed to help users retrieve information from both personal knowledge bases and the public web through a unified interface. The project combines retrieval-augmented search with AI summarization to deliver concise answers instead of forcing users to manually sift through multiple sources. It supports multiple AI models and search providers, enabling flexible configuration depending on cost, performance, or privacy requirements. Beyond search, memfree includes an AI Page Generator that can transform text or images into production-ready frontend code using modern web stacks. ... -
6
LM Studio CLI (lms)
LM Studio CLI
LM Studio CLI (lms) is a command-line tool designed to help developers manage and interact with LM Studio directly from the terminal. Built with lmstudio.js, it provides a streamlined interface for controlling local language models and API server operations. The CLI ships with LM Studio 0.2.22 and newer, making it easy to manage models without additional complex setup. With simple subcommands, users can check system status, start or stop the local server, and monitor logs in real time. It also enables users to load, unload, and list models for efficient inferencing workflows. ... -
7
Briefer
Dashboards and notebooks in a single place
...It’s designed so technical users can write Markdown, SQL, and Python side by side for data analysis, visualization, and reporting, while non-technical viewers can interact with results through inputs, dropdowns, and date pickers without writing any code. Users work in a Notion-style interface where they can build, organize, and share pages that contain executable code blocks, charts, text explanations, and interactive elements within the same document, enabling rich data storytelling and reproducible analytics. Briefer supports real-time collaboration, meaning multiple teammates can edit the same notebook or dashboard simultaneously and see changes live, which encourages shared analysis and decision making. -
8
Secure OpenClaw
A personal 24x7 AI assistant like OpenClaw
...Unlike a traditional chatbot that lives in a browser or API dashboard, Secure-OpenClaw runs locally or on your chosen infrastructure and listens for messages on channels you already use, giving you an always-on interface to a powerful agent. It leverages Claude and other models to interpret messages and is built to manage persistent memory, scheduled reminders, and integration with hundreds of third-party apps to automate workflows without leaving your chat. The design emphasizes security and autonomy by allowing you to maintain ownership of your data and run the system within your trusted environment, while still harnessing advanced AI capabilities. -
9
VibeTensor
Our first fully AI generated deep learning system
...What makes VibeTensor remarkable is that every major component, from core libraries and dispatch systems to CUDA runtime support, caching allocators, and language bindings, was created and validated by coding agents using automated builds and tests rather than manual line-by-line human coding. The system includes both a Python frontend via a torch-like API and an experimental Node.js/TypeScript interface. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
CineCLI
CineCLI is a cross-platform command-line movie browser
CineCLI is a command-line utility designed to help movie lovers quickly browse, search, and access film information from the terminal without needing a graphical interface. It connects to popular online movie databases to fetch metadata such as titles, release dates, ratings, genres, casts, posters, and plot summaries, presenting all of that in a concise, text-friendly format suitable for terminals or scripts. Users can search by keyword, year, or exact title and then drill into detailed views for individual films, making it useful for creating watchlists, learning more about films before watching, or integrating movie lookup into shell workflows. ... -
11
jsconsole
Web based console - for presentations and workshops
jsconsole is a web-based interactive JavaScript console designed to make it easy to run and present live JavaScript code directly in the browser, which is especially handy for workshops, presentations, and remote debugging scenarios. It provides an in-browser REPL-style environment where you can type JS expressions and see output instantly, making it useful for teaching, debugging snippets, or demonstrating ideas without setting up a local development environment. One hallmark of jsconsole... -
12
vim-autoformat
Provide code formatting in Vim by integrating existing code formatters
vim-autoformat is a universal “format this buffer” interface for Vim and Neovim that routes your file through the right external formatter with a single command. Instead of remembering dozens of tool names and CLI flags, you call one mapping and the plugin picks an appropriate backend based on filetype and configuration. It supports a wide range of formatters—such as Black, isort, yapf, Prettier, clang-format, gofmt, rustfmt, shfmt, and many more—while letting you override arguments per project or per filetype. ... -
13
4M
4M: Massively Multimodal Masked Modeling
4M is a training framework for “any-to-any” vision foundation models that uses tokenization and masking to scale across many modalities and tasks. The same model family can classify, segment, detect, caption, and even generate images, with a single interface for both discriminative and generative use. The repository releases code and models for multiple variants (e.g., 4M-7 and 4M-21), emphasizing transfer to unseen tasks and modalities. Training/inference configs and issues discuss things like depth tokenizers, input masks for generation, and CUDA build questions, signaling active research iteration. ... -
14
DreamCraft3D
Official implementation of DreamCraft3D
DreamCraft3D is DeepSeek’s generative 3D modeling framework / model family that likely extends their earlier 3D efforts (e.g. Shap-E or Point-E style models) with more capability, control, or expression. The name suggests a “dream crafting” metaphor—users probably supply textual or image prompts and generate 3D assets (point clouds, meshes, scenes). The repository includes model code, inference scripts, sample prompts, and possibly dataset preparation pipelines. It may integrate rendering or... -
15
3FS
A high-performance distributed file system
...Its primary aim is to support efficient and scalable feature transformation pipelines—especially for inference environments—by batching, caching, and integrating feature-based modules like segmenters, sparse retrievers, and scorers seamlessly. The repo includes APIs to define components (e.g. seg, ret, scor) that wrap or interface with external or internal modules, as well as logic to schedule and compose these feature transforms. By handling caching and batching at a system level, 3FS helps reduce overhead when many features or modules must be evaluated per input (e.g. in an LLM agent pipeline). The repository includes example integration with models like DeepSeek-V2 / V3, showing how 3FS can be plugged into pipelines for operations like plugin processing. -
16
Geocoder
Complete Ruby geocoding solution
...With its database integration, you can query for nearby records, order results by distance, or filter results within a radius, making it invaluable for location-based apps. By abstracting away API differences and providing a clean Ruby interface, Geocoder makes geospatial features straightforward to implement in web and mobile projects. -
17
future
R package: future: Unified Parallel and Distributed Processing in R
The future package in R provides a unified abstraction for asynchronous and/or parallel computation. It allows R expressions to be scheduled for future evaluation, with the result retrieved later, in a way decoupled from the specific backend used. This lets code be written in a way that works with sequential execution, multicore, multisession, cluster, or remote compute backends, without changing the high-level code. It handles automatic exporting of needed global variables/functions,... -
18
PowerHub
A post exploitation tool based on a web application
PowerHub is a PowerShell-based automation framework designed to centralize and orchestrate common administrative tasks across Windows environments. It exposes a modular command set for inventorying systems, managing services, deploying packages, and executing remote commands with consistent logging and error handling. The project places emphasis on discoverability and reuse: scripts are organized into reusable modules and functions with clear parameter contracts so teams can compose... -
19
Clouddriver
Read and write operations across cloud providers
Clouddriver is the cloud-provider integration layer of Spinnaker, exposing a uniform API and cache for infrastructure resources across multiple clouds. It discovers and tracks entities such as server groups, load balancers, security groups, images, and instances, normalizing them so higher-level services can reason consistently. The service also brokers mutating operations—like creating server groups or resizing clusters—by translating Spinnaker requests into provider-specific calls. A... -
20
Docspell
Assist in organizing your piles of documents
Docspell is a personal document organizer. Or sometimes called a "Document Management System" (DMS). You'll need a scanner to convert your papers into files. Docspell can then assist in organizing the resulting mess. It can unify your files from scanners, emails, and other sources. It is targeted for home use, i.e. families, households, and also for smaller groups/companies. You can associate tags, set correspondent,s and lots of other predefined and custom metadata. If your documents are... -
21
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
When I first found FastAPI, I got it immediately. I was excited to find something so innovative and ergonomic built on Pydantic. Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we began to use LLMs in Pydantic Logfire, I couldn't find anything that gave me the same feeling. PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer... -
22
Data Formulator
Create rich visualizations with AI
To create rich visualizations, data analysts often need to iterate back and forth among data processing and chart specification to achieve their goals. To achieve this, analysts need not only proficiency in data transformation and visualization tools but also efforts to manage the branching history consisting of many different versions of data and charts. Recent LLM-powered AI systems have greatly improved visualization authoring experiences, for example by mitigating manual data... -
23
OpenCompass
OpenCompass is an LLM evaluation platform
Just like a compass guides us on our journey, OpenCompass will guide you through the complex landscape of evaluating large language models. With its powerful algorithms and intuitive interface, OpenCompass makes it easy to assess the quality and effectiveness of your NLP models. OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 50+ datasets with about 300,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. ... -
24
faasd
A lightweight & portable faas engine
faasd is OpenFaaS reimagined but without the cost and complexity of Kubernetes. It runs on a single host with very modest requirements, making it fast and easy to manage. Under the hood it uses containers and Container Networking Interface (CNI) along with the same core OpenFaaS components from the main project. To deploy microservices and functions that you can update and monitor remotely. When you don't have the bandwidth to learn or manage Kubernetes. To deploy embedded apps in IoT and edge use-cases. To distribute applications to a customer or client. You have a cost sensitive project - run faasd on a 1GB VM for 5-10 USD / mo or on your Raspberry Pi. ... -
25
optparse-applicative
Applicative option parser
optparse-applicative is a haskell library for parsing options on the command line, and providing a powerful applicative interface for composing them. optparse-applicative takes care of reading and validating the arguments passed to the command line, handling and reporting errors, generating a usage line, a comprehensive help screen, and enabling context-sensitive bash, zsh, and fish completions. A value of type Parser a represents a specification for a set of options, which will yield a value of type a when the command line arguments are successfully parsed. ...
