Search Results for "framework" - Page 64
Sort By:
Showing 12086 open source projects for "framework"
View related business solutions-
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.
-
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
1
OpenAGI
When LLM Meets Domain Experts
OpenAGI is a package for AI agent creation designed to connect large language models with domain-specific tools and workflows in the AIOS (AI Operating System) ecosystem. It provides a structured Python framework, pyopenagi, for defining agents as modular units that encapsulate execution logic, configuration, and dependency metadata. Agents are organized in a well-defined folder structure that includes code (agent.py), configuration (config.json), and extra requirements (meta_requirements.txt), which makes them easy to package, share, and reuse. ... -
2
Animated Drawings
Code to accompany "A Method for Animating Children's Drawings"
AnimatedDrawings is a framework that converts user sketches or line drawings into fully animated 2D motion sequences using learned motion priors. The idea is that you draw a simple static figure (stick figure, silhouette, or contour lines), and the system produces plausible skeletal motion (walking, jumping, dancing) that adheres to the drawn shape constraints. -
3
CogView4
CogView4, CogView3-Plus and CogView3(ECCV 2024)
CogView4 is the latest generation in the CogView series of vision-language foundation models, developed as a bilingual (Chinese and English) open-source system for high-quality image understanding and generation. Built on top of the GLM framework, it supports multimodal tasks including text-to-image synthesis, image captioning, and visual reasoning. Compared to previous CogView versions, CogView4 introduces architectural upgrades, improved training pipelines, and larger-scale datasets, enabling stronger alignment between textual prompts and generated visual content. It emphasizes bilingual usability, making it well-suited for cross-lingual multimodal applications. ... -
4
Moshi
A speech-text foundation model for real time dialogue
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). -
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.
-
5
Filesystem
An implementation of C++17 std::filesystem
This is a header-only single-file std::filesystem compatible helper library, based on the C++17 and C++20 specs, but implemented for C++11, C++14, C++17 or C++20 (tightly following the C++17 standard with very few documented exceptions). It is currently tested on macOS 10.12/10.14/10.15/11.6, Windows 10, Ubuntu 18.04, Ubuntu 20.04, CentOS 7, CentOS 8, FreeBSD 12, Alpine ARM/ARM64 Linux and Solaris 10 but should work on other systems too, as long as you have at least a C++11 compatible... -
6
csharp-ls
Roslyn-based LSP language server for C#
This is a hacky Roslyn-based LSP server for C#, as an alternative to omnisharp-roslyn. csharp-ls requires .NET 7 SDK to be installed. However, it has been reported to work with projects using older versions of dotnet SDK, including .NET Core 3, .NET Framework 4.8 and possibly older ones too as it uses the standard Roslyn/MSBuild libs that Visual Studio & omnisharp does. csharp-ls implements the standard LSP protocol to interact with your editor. However there are some features that need a non-standard implementation and this is where editor-specific plugins can be helpful. Supports automatic installation, go-to-metatada (can view code from nuget/compiled dlls) and some additional features. -
7
PeachPie
PeachPie, the PHP compiler and runtime for .NET and .NET Core
PeachPie is a modern PHP compiler based on the Microsoft Roslyn compiler platform and drawing from our popular Phalanger project. It allows PHP to be executed within the .NET framework, thereby opening the door for PHP developers into the world of .NET – and vice versa. Build, debug, profile, and diagnose your code in the family of .NET tools, including Visual Studio and VS Code. Seamlessly port your legacy PHP code to the modern, cross-platform, lightning-fast .NET Core. Leverage the best of both worlds and build .NET apps in C# and PHP. ... -
8
ZenML
Build portable, production-ready MLOps pipelines
A simple yet powerful open-source framework that scales your MLOps stack with your needs. Set up ZenML in a matter of minutes, and start with all the tools you already use. Gradually scale up your MLOps stack by switching out components whenever your training or deployment requirements change. Keep up with the latest changes in the MLOps world and easily integrate any new developments. -
9
DeepLabCut
Implementation of DeepLabCut
DeepLabCut™ is an efficient method for 2D and 3D markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results (i.e. you can match human labeling accuracy) with minimal training data (typically 50-200 frames). We demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors. The package is open source, fast, robust, and can be used to compute 3D pose estimates or for multi-animals. Please see the original paper and the latest work below! This package is collaboratively developed by the Mathis Group & Mathis Lab at EPFL (releases prior to 2.1.9 were developed at Harvard University). ... -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
10
C Unit Testing Framework
Automated testing framework for C'
Automated testing framework for 'C'. -
11
Plutus
The Plutus language implementation and tools
Plutus is the smart contract development framework for the Cardano blockchain, created using Haskell. It provides the core infrastructure for writing, testing, and deploying secure, deterministic smart contracts on the Cardano platform. Plutus includes a custom functional language (Plutus Core), a higher-level embedded DSL (Plutus Tx) for writing contracts in Haskell, and an off-chain infrastructure for managing interactions. -
12
Maelstrom
A workbench for writing toy implementations of distributed systems
...It provides standardized JSON-based protocols and test harnesses (via Jepsen) to validate the behavior of custom toy systems—like commutative sets or transactional key-value stores—under simulated failure conditions. You implement your server in any language, connect through stdin/stdout, and the framework injects network disruptions, partitions, and consistency checks. -
13
Vito
Free and Self-Hosted Server Management Tool
Vito is an open-source deployment tool designed for PHP projects. It provides a simple and automated way to deploy code to remote servers using SSH. With Vito, developers can define deployment workflows in configuration files, ensuring consistency and repeatability. It is lightweight, easy to set up, and suitable for teams looking to automate deployments without the overhead of large CI/CD platforms. -
14
HiClaw
An open source collaborative multi-agent OS
HiClaw is an AI-powered legal assistant framework developed within the AgentScope ecosystem to support intelligent legal reasoning, document analysis, and workflow automation for legal research and compliance tasks. The project combines large language models with agent orchestration systems to process legal documents, interpret regulations, summarize contracts, and assist with legal knowledge retrieval. -
15
templUI
A growing collection of beautifully designed UI components for Go
templUI is a modern UI component library built specifically for Go applications using the templ templating language, offering a developer-first approach to building interfaces with strong type safety and performance. It provides a growing collection of beautifully designed, production-ready components styled with Tailwind CSS, allowing developers to construct modern web interfaces without relying on heavy frontend frameworks. One of its defining principles is code ownership, meaning... -
16
Stlite
n-browser Streamlit
Stlite is a WebAssembly-powered framework that enables Streamlit applications to run entirely in the browser without requiring a Python backend server. It achieves this by using Pyodide, a WebAssembly-based Python runtime, to execute Python code directly within the browser environment. This allows developers to build interactive data applications using familiar Streamlit APIs while eliminating the need for server-side infrastructure. -
17
Claude Subconscious
Give Claude Code a subconscious
Claude Subconscious is an experimental plugin that enhances AI coding workflows by introducing a persistent “memory layer” for Claude Code through integration with Letta’s agent framework. It operates as a background agent that continuously observes user interactions, reads project files, and processes session transcripts to build long-term contextual memory. Unlike standard AI interactions that reset between sessions, this system accumulates knowledge over time, allowing it to recall user preferences, project structures, and recurring patterns across multiple sessions. ... -
18
model2Vec
Fast State-of-the-Art Static Embeddings
model2vec is an innovative embedding framework that converts large sentence transformer models into compact, high-speed static embedding models while preserving much of their semantic performance. The project focuses on dramatically reducing the computational cost of generating embeddings, achieving significant improvements in speed and model size without requiring large datasets for retraining. -
19
BehaviorTree.CPP
C++ behavior tree library for robotics and AI decision systems
BehaviorTree.CPP is a C++ library designed to create, manage, and execute behavior trees, a widely used model for decision-making in robotics and artificial intelligence systems. It provides a flexible and modular framework that allows developers to define complex behaviors as reusable tree structures composed of nodes. BehaviorTree.CPP emphasizes performance and real-time execution, making it particularly suitable for robotics applications where responsiveness is critical. It supports asynchronous actions, enabling long-running tasks without blocking the execution of the entire tree. ... -
20
Ollamac
Mac app for Ollama
Ollamac is an open-source native macOS application that provides a graphical interface for interacting with local large language models running through the Ollama inference framework. The project was created to simplify the process of using local AI models, which typically require command-line interaction, by offering a clean and intuitive desktop interface. Through this interface, users can run and chat with a variety of LLM models installed through Ollama directly on their own machines. The application focuses on delivering a lightweight and responsive experience that integrates seamlessly with the macOS ecosystem. ... -
21
Aix-DB
Based on the LangChain/LangGraph framework
Aix-DB is an open-source intelligent data analysis platform that combines large language models with database technologies to enable conversational data exploration. The system is designed as a ChatBI solution that allows users to query datasets using natural language and receive structured insights, charts, and visualizations automatically. Built on frameworks such as LangChain and LangGraph, Aix-DB integrates retrieval-augmented generation and Text-to-SQL capabilities to convert user... -
22
WeClone
One-stop solution for creating your digital avatar from chat history
WeClone is an open source AI project designed to replicate a person’s conversational style and personality by training models on chat history data. The system analyzes message patterns, linguistic style, and contextual behavior in order to generate responses that resemble the original user’s communication style. It is intended primarily as an experimental exploration of digital personality modeling and conversational AI personalization. By processing large volumes of conversation data,... -
23
GuitarPedal
Linus learns analog circuits
...The project demonstrates how to read audio input, process it through simple transformations, and write the result out in real time with minimal latency. It emphasizes straightforward, inspectable DSP so developers can follow the math and tweak parameters without a giant framework in the way. The codebase favors portability and simplicity, focusing on a handful of canonical effects rather than a sprawling plugin architecture. It doubles as a teaching aid for musicians who code, showing how buffers, sampling rates, and numerical stability affect tone. While not a full multi-FX suite, it offers a compact sandbox for experimenting with guitar processing on modest hardware. -
24
Coconut
Training Large Language Model to Reason in a Continuous Latent Space
Coconut is the official PyTorch implementation of the research paper “Training Large Language Models to Reason in a Continuous Latent Space.” The framework introduces a novel method for enhancing large language models (LLMs) with continuous latent reasoning steps, enabling them to generate and refine reasoning chains within a learned latent space rather than relying solely on discrete symbolic reasoning. It supports training across multiple reasoning paradigms—including standard Chain-of-Thought (CoT), no-thought, and hybrid configurations—using configurable training stages and latent representations. ... -
25
Algora TV
Open source Twitch for developers
...The project enables developers to monetize their live content while providing devtools companies a dynamic and non-intrusive way to reach audiences in real time. Built on top of the Phoenix framework, it leverages Elixir’s concurrency and scalability to handle streaming, ad management, and user interactions seamlessly. The system integrates with GitHub for authentication and uses Tigris for media storage and delivery, with optional support for services like FFmpeg, ImageMagick, and OBS Studio for livestream testing and video processing. ...