Search Results for "switching" - Page 5
Sort By:
Showing 463 open source projects for "switching"
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.
-
$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
Reins
Ollama client that simplifies experimenting with LLMs
Reins is a privacy-first, multi-platform AI client designed to simplify and enhance interaction with Ollama-based language models. It provides a highly customizable chat interface where users can configure system prompts, switch models dynamically, and adjust inference parameters such as temperature, token limits, and context size on a per-conversation basis. The application is built to run across platforms including mobile and desktop environments, making it accessible for a wide range of... -
2
AssemblyScript
A TypeScript-like language for WebAssembly
...The language is optimized for generating efficient and compact WebAssembly modules, making it suitable for performance-critical applications in both browser and server environments. Its design bridges the gap between high-level scripting and low-level execution, allowing developers to achieve near-native performance without switching to languages like C or Rust. AssemblyScript integrates with the WebAssembly ecosystem, enabling seamless interaction with JavaScript through standard APIs. It is widely used in scenarios where performance and portability are essential, such as gaming, data processing, and edge computing. -
3
II Agent
A new open-source framework to build and deploy intelligent agents
II-Agent is an open-source intelligent assistant framework designed to automate complex workflows across multiple domains using large language models and external tools. The platform allows users to interact with multiple AI models within a single environment while connecting those models to external services and knowledge sources. Through a unified interface, users can switch between models, access specialized tools, and execute tasks that require information retrieval, code execution, or... -
4
dsh-market
The plugin market inside DeepSeek Harness, browse, search, one-click
dsh-market is an integrated plugin marketplace for discovering and managing extensions inside DeepSeek Harness. It provides browsing and search across a large community catalog with categories, popularity information, screenshots, sorting, and bilingual descriptions. Plugins can be installed through a confirmation workflow with live progress and can often become active after a simple page refresh. The marketplace also manages themes that can be installed and switched immediately without... -
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
vinext-starter
An interactive 3D human anatomy explorer built using threejs
...Additional activities include guided lessons, quick quizzes, function animations, microscopic views, and organ comparisons. The interface prefetches models and image assets to make switching between specimens feel responsive. The application is built with React, Three.js-based rendering, GSAP interface animation, and a modern full-stack web starter with optional Cloudflare services. -
6
ikun-ui
A Svelte.js based UnoCSS UI library that allows you to make websites
...IKun UI also supports integration with Iconify, giving developers access to a vast library of icons for enhancing interface design. It includes built-in support for dark mode and theme switching, making it easy to adapt applications to different visual preferences. Designed for performance and ease of use, it works seamlessly with Svelte and modern browsers, ensuring smooth rendering and responsiveness. -
7
CC Mirror
Create multiple isolated Claude Code variants with custom providers
...Rather than running a single global Claude Code installation, cc-mirror creates separate instances — each with its own config, session store, prompt packs, theme tweaks, and optional preloaded skills — so you can tailor different environments for specific tasks, teams, or experimentation without polluting your primary setup. It also includes an interactive terminal UI for discovering, creating, and launching these isolated variants with a single command, making setup and switching effortless. For teams, cc-mirror’s team mode brings shared task storage and coordinated multi-agent workflows using shared goals and task lists that agents can collaborate on; this is useful for scaling up agentic coding across complex projects. -
8
Antigravity Claude Proxy
Proxy that exposes Antigravity provided claude / gemini models
...This makes it easier to integrate Claude into existing toolchains, scripts, notebooks, or agent frameworks that do not have built-in support for Anthropic’s native SDKs. It abstracts away key differences like authentication choreography, request schema quirks, and streaming protocols so client code can remain unchanged when switching between models. -
9
xxh
Bring your favorite shell wherever you go through the ssh
You stuffed the command shell with aliases, tools and colors but you lose it all when using ssh. The mission of xxh is to bring your favorite shell wherever you go through ssh without root access and system installations. Preparing portable shells and plugins occurs locally and then xxh uploads the result to the host. No installations or root access on the host is required. Security and host environment are a prime focus. No blindfold copying config files from local to the remote host.... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Happy Coder
Mobile and Web client for Codex and Claude Code, with realtime voice
Happy is an open-source, cross-platform mobile and web client designed to bring powerful AI coding agents such as Claude Code and Codex to your fingertips no matter where you are. At its core, Happy wraps existing AI coding tools with a unified interface, providing real-time voice interactions, encrypted communication, and seamless device switching between desktop and mobile. You can start a coding session locally through the Happy CLI or connect from a phone or browser, allowing developers to inspect, interact with, and guide the AI as it generates, tests, or explains code. The project includes components like a dedicated backend server for encrypted sync, a rich front-end experience across web and native apps, and support for push notifications when your coding agent encounters permission requests or errors. ... -
11
Positron
Positron, a next-generation data science IDE
...It aims to unify exploratory data analysis, production code, and data-app authoring in a single environment so that data scientists move from “question → insight → application” without switching tools. Built on the open-source Code-OSS foundation, Positron provides a familiar coding experience along with specialized panes and tooling for variable inspection, data-frame viewing, plotting previews, and interactive consoles designed for analytical work. The IDE supports notebook and script workflows, integration of data-app frameworks (such as Shiny, Streamlit, Dash), database and cloud connections, and built-in AI-assisted capabilities to help write code, explore data, and build models. -
12
Elia
Terminal-based LLM chat tool with multi-model and local support
Elia is an open source terminal-based interface designed for interacting with large language models in a fast and efficient way. It runs entirely in the command line, offering a keyboard-driven experience that reduces the need for switching between apps. Users can chat with both proprietary models like ChatGPT and Claude, as well as local models such as Llama 3, Mistral, and Gemma. Elia stores conversations in a local SQLite database, making it easy to revisit past interactions. It supports flexible usage with inline and full-screen chat modes, along with simple configuration through a single file. ... -
13
Situation Monitor
Real-time dashboard for monitoring global news and markets
Situation Monitor is an open-source real-time dashboard designed to aggregate and visualize global information streams related to news, financial markets, technology, and geopolitical developments. The project aims to provide a centralized situational awareness interface where users can observe multiple sources of high-signal information without constantly switching between separate applications or websites. Instead of functioning as a traditional news reader, the platform is designed more like an intelligence monitoring system that highlights important signals from diverse data feeds. The dashboard aggregates real-time updates about economic indicators, corporate developments, geopolitical events, and other macro-level signals that may influence markets or public discourse. ... -
14
Authentic Theme
Official theme for the best server management panel
Authentic Theme is a modern, responsive skin for the Webmin/Uberspace control panels that updates the look, feel, and usability of interface components. It replaces the default UI layout and navigation, adding sidebars, iconography, contextual menus, tabs, and dynamic theme options to enhance both aesthetics and workflow. The theme supports multiple screen sizes and devices, adapting elements like menus and panels to maintain usability on narrow windows. It also integrates customization... -
15
Casbin
An authorization library that supports access control models
An authorization library that supports access control models like ACL, RBAC, ABAC for Golang, Java, C/C++, Node.js, Javascript, PHP, Laravel, Python, .NET (C#), Delphi, Rust, Ruby, Swift (Objective-C), Lua (OpenResty), Dart (Flutter) and Elixir. In Casbin, an access control model is abstracted into a CONF file based on the PERM metamodel (Policy, Effect, Request, Matchers). So switching or upgrading the authorization mechanism for a project is just as simple as modifying a configuration. Besides memory and file, Casbin policy can be stored into lots of places. Currently, dozens of databases are supported, from MySQL, Postgres, Oracle to MongoDB, Redis, Cassandra, AWS S3. Check the full supported list at: adapters. ... -
16
FRRouting
The FRRouting Protocol Suite
...FRR’s seamless integration with native Linux/Unix IP networking stacks makes it a general-purpose routing stack applicable to a wide variety of use cases including connecting hosts/VMs/containers to the network, advertising network services, LAN switching and routing Internet access routers, and Internet peering. FRR has its roots in the Quagga project. In fact, it was started by many long-time Quagga developers who combined their efforts to improve on Quagga’s well-established foundation in order to create the best routing protocol stack available. We invite you to participate in the FRRouting community and help shape the future of networking. -
17
ice
The progressive framework based on React
...Inspiring traditional design cognition combined with design trends, and deriving a new platform product design language. Provide a variety of vertical field templates and blocks, quickly create projects, support style switching, and meet individual needs. Free collocation of materials, integration of development and debugging, covering the whole process management of project research and development, ready to use out of the box. Make front-end development faster, better, and easier. More than 400 projects are in use, continuous, reliable and stable, immediate and effective service. -
18
Site Kit for WordPress
Site Kit is a one-stop solution for WordPress users
...It also handles authentication and permission scopes securely, so multiple collaborators can access insights without sharing credentials. Widgets and contextual panels put data where it’s needed—for example, on the post list or edit screen—reducing tab-switching. For developers and agencies, Site Kit simplifies client onboarding and standardizes reporting across many sites. -
19
Wave Terminal
An open-source, cross-platform terminal for seamless workflows
Wave is an open-source AI-native terminal built for seamless workflows. Wave isn't just another terminal emulator; it's a rethink on how terminals are built. Wave combines the command line with the power of the open web to help veteran CLI users and new developers alike. Keep development moving forward without the copy, pasting, saving, and exporting headache. Built on an open web framework that is fully extensible. Quickly edit code on a local or remote machine with the same editor that... -
20
Discord Ollama Integration
Discord Bot that utilizes Ollama to interact with any LLMs
...The project is designed to turn any Discord channel into an interactive AI assistant powered by locally hosted large language models, allowing users to chat, manage models, and control AI behavior through slash commands. It includes extensive command support for tasks such as summarization, model switching, listing available models, and pulling new models from the Ollama library. The system is built with multi-user support in mind, enabling simultaneous conversations while maintaining contextual awareness at the channel and user level. It also handles long outputs by splitting responses beyond Discord’s message limits, ensuring smooth interaction even with large generated responses. ... -
21
LoLLMs WEBUI
Local AI WebUI for running and managing large language models offlineA
lollms-webui is a locally hosted web interface designed to run and manage large language models without relying on external services. It provides users with a centralized environment to interact with multiple AI models, making it suitable for experimentation, development, and personal use. lollms-webui emphasizes offline capability, allowing users to maintain privacy and control over their data while still accessing advanced AI features. It integrates model management tools that help users... -
22
Agently 4
Build GenAI application quick and easy
Agently is a Python framework for building generative-AI (“GenAI”) applications; it focuses on enabling developers to orchestrate AI agents, workflows, and event-driven logic in a robust, reusable way. With Agently, one can define agents that call different models, chain tasks, trigger workflows based on events, and switch models with minimal code changes. It abstracts away boilerplate around model API calls, tool usage, prompt management, and workflow state. The project aims at... -
23
Jekyll Picture Tag
Easy responsive images for Jekyll
...Jekyll Picture Tag automatically builds cropped, resized, and reformatted images, builds several kinds of markup, offers extensive configuration while requiring none, and solves both the art direction and resolution switching problems with a little YAML configuration and a simple template tag. -
24
any-agent
A single interface to use and evaluate different agent frameworks
any-agent is a Python library that provides a unified interface for working with multiple agent frameworks, allowing developers to create, run, and evaluate AI agents without being locked into a single ecosystem. It abstracts the differences between frameworks such as LangChain, LlamaIndex, OpenAI Agents, and others, enabling users to switch between them with minimal configuration changes. The library is designed to simplify experimentation and benchmarking, making it easier to compare agent... -
25
MemOS
AI memory OS for LLM and Agent systems
...The project explores rethinking system abstractions by tightly coupling computation with memory objects so that programs can operate on large datasets without expensive serialization or context switching. It aims to support advanced workflows like persistent in-memory data structures, crash-resilient state handling, and seamless sharing of data across tasks without copying. By abandoning some of the historical assumptions of Unix-style operating systems, MemOS attempts to unlock new performance and scalability tradeoffs for applications that need high throughput and low latency on memory-intensive workloads.
