Search Results for "context" - Page 17
Sort By:
Showing 2139 open source projects for "context"
View related business solutions-
$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.
-
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.
-
1
MediaCrawler
Self-media platform crawler
...It supports Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, Zhihu, and other services. The project uses Playwright to automate browser login and preserve authenticated sessions. It obtains required request signatures from the active browser context, avoiding complex JavaScript reverse engineering. Users can search by keyword, crawl specific posts, collect nested comments, and retrieve creator profiles. It also supports cached login states, proxy pools, and comment word-cloud generation. The repository is intended for learning and research, with clear restrictions against illegal, large-scale, or commercial scraping. -
2
Antigravity CLI
The CLI understands codebases, makes edits and executes commands
Antigravity CLI is Google’s command-line AI coding agent for working with a codebase directly from the terminal. It can understand project context, make code edits with user permission, and execute commands as part of an agent-assisted development workflow. The tool is positioned as part of Google Antigravity’s newer agent-first platform and succeeds key Gemini CLI workflows while adding a more robust foundation for complex coding tasks. It supports important agent capabilities such as Agent Skills, Hooks, Subagents, and Antigravity plugins. ... -
3
OpenAI Privacy Filter
Bidirectional token-classification model for identifiable info
...It operates as a bidirectional token classification system that labels sensitive data in a single forward pass rather than generating text sequentially, enabling fast processing for large datasets. The model supports long-context inputs, allowing it to analyze extensive documents without chunking, which improves consistency in redaction tasks. It can run locally on standard hardware, ensuring that sensitive information never leaves the user’s environment and supporting privacy-first workflows. The system is fine-tunable, enabling adaptation to specific datasets or compliance requirements across industries. ... -
4
MemPalace
The highest-scoring AI memory system ever benchmarked
...It operates fully locally using tools like ChromaDB, meaning it requires no API keys, cloud services, or external dependencies once installed. MemPalace emphasizes fidelity over compression, preserving full conversational history to maintain reasoning, nuance, and decision-making context that is typically lost in other systems. -
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.
-
5
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. ... -
6
Lazydocker
The lazier way to manage everything docker
LazyDocker is an interactive terminal GUI (built with gocui in Go) for managing Docker and Docker Compose. It lets users monitor containers, images, volumes, and networks from the command line, reducing context switching. -
7
Verible
Verible is a suite of SystemVerilog developer tools
The Verible project's main mission is to parse SystemVerilog (IEEE 1800-2017) (as standardized in the SV-LRM) for a wide variety of applications, including developer tools. It was born out of a need to parse un-preprocessed source files, which is suitable for single-file applications like style-linting and formatting. In doing so, it can be adapted to parse preprocessed source files, which is what real compilers and toolchains require. The spirit of the project is that no-one should ever... -
8
Hexis
Git-backed control plane for AI-agent skills, tools, context, identity
...Everything is stored in a Git repository controlled by the organization, giving teams branches, history, change review, and rollback. Role-based access determines which skills, tools, and context each employee and agent can use. A built-in remote MCP server lets compatible clients such as Claude, ChatGPT, Cursor, and Cline connect to the same governed workspace. Tool manuals can include encrypted secrets without exposing credentials directly to agents. Proposed skill changes can move through owner approval before they become available to the wider team. ... -
9
Harness-1
Ultra Recipe for Training Long-Horizon Search Agents
...It is designed for long-horizon search tasks where the model must search, inspect documents, curate evidence, verify claims, and decide when enough evidence has been gathered. The harness externalizes search state, including candidate documents, evidence links, verification records, and budget-aware context. This lets the policy focus on higher-level decisions instead of trying to keep every detail inside the model context. The repository includes inference utilities, training scripts, evaluation runners, dataset tools, and documentation for running the released checkpoint. Its main value is showing how a smaller open model can approach advanced search-agent behavior through structured retrieval state and reinforcement learning. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
10
HyperFrames
Write HTML. Render video. Built for agents
HyperFrames is a framework developed by HeyGen that focuses on generating and managing structured, dynamic content experiences powered by AI. It introduces the concept of “frames,” which represent modular units of content that can be dynamically composed and rendered based on context or user interaction. The system is designed to enable highly interactive and personalized experiences, particularly in applications such as video generation, storytelling, and user interfaces. It supports integration with AI models to generate or modify content within these frames, allowing real-time adaptation. The framework emphasizes composability, enabling developers to build complex experiences by combining smaller units. ... -
11
ViMax
Director, Screenwriter, Producer, and Video Generator All-in-One
...ViMax’s design accommodates large image sets and supports retrieval augmentation, enabling it to work with external image databases, supplementary metadata, and semantic search to enhance context awareness. The system aims to bridge foundational vision backbones and generative language models through adapters and fusion layers that maximize both signal integration and reasoning depth, and includes utility pipelines for training, evaluation, and deployment. -
12
GLM
OpenGL Mathematics (GLM)
...This library works perfectly with OpenGL but it also ensures interoperability with other third party libraries and SDK. It is a good candidate for software rendering (raytracing / rasterisation), image processing, physics simulations and any development context that requires a simple and convenient mathematics library. GLM is written in C++98 but can take advantage of C++11 when supported by the compiler. -
13
Copilot for Obsidian
AI assistant plugin that brings chat, search, and agents to Obsidian
...It enables users to interact with their notes through conversational chat, allowing them to ask questions, summarize information, and generate new content using large language models. It works inside a user’s vault and can analyze notes, documents, and other referenced materials to provide context-aware responses. It supports multiple AI providers and models, giving users the flexibility to choose external APIs or run compatible local models depending on their setup. Obsidian Copilot emphasizes user ownership of data by keeping notes in the local Obsidian vault while allowing the AI to process them as context when requested. ... -
14
Google Workspace MCP Server
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms
Google Workspace MCP is an open-source server that connects AI assistants to Google Workspace services through the Model Context Protocol (MCP), allowing large language models to interact directly with productivity tools. The project exposes a wide set of Google services including Gmail, Google Drive, Docs, Sheets, Slides, Calendar, Chat, and other Workspace components as structured tools that an AI system can call programmatically. By acting as a bridge between AI clients and the Google ecosystem, the server enables automated workflows such as searching emails, creating calendar events, retrieving documents, or editing files without leaving the AI environment. ... -
15
Chrome DevTools MCP
Chrome DevTools for coding agents
chrome-devtools-mcp is an MCP server that connects AI agents to the Chrome DevTools Protocol so they can inspect pages, record traces, read console/network data, and modify the live browser state under user control. It makes a running Chrome instance visible to MCP clients, enabling agents to debug websites end-to-end—launching Chrome, navigating, profiling, and collecting artifacts in a structured way. The repository spells out environment requirements and cautions that exposing a live... -
16
Complete Intro to React v8
The Complete Intro to React, as taught by Brian Holt
...It begins with React without heavy tooling, then introduces modern JavaScript tools and core component concepts. Learners work with JSX, props, state, effects, hooks, context, routing, and specialized React APIs. Later modules cover performance, low-priority rendering, TypeScript, Redux, Tailwind CSS, and application testing. The repository hosts the course website and written lessons, while a separate project repository provides step-by-step application files. Its organized sections let students move from fundamentals into production-oriented patterns. ... -
17
git-messenger.vim
Vim and Neovim plugin to reveal the commit messages
...It can also show the diff for a selected commit, including options for unified and word diffs. This makes it useful when reading unfamiliar code, reviewing history, or debugging changes with context from version control. -
18
Ralph Wiggum Marketer
A Claude Code Plugin that provides an autonomous AI copywriter
...It leverages the Ralph Wiggum loop concept — a continuous iteration pattern named after the iconic character that symbolizes persistent, repeated refinement — to let Claude Code keep iterating on content until predefined completion criteria are met, rather than stopping after a single output. This plugin integrates with Claude Code workflows so that marketers or product teams can define high-level goals, seed their product or service context, and then have the AI autonomously draft, refine, and polish marketing materials with minimal human intervention. -
19
Gpg4win
GnuPG for Windows
Gpg4win is the official Windows distribution of the GnuPG encryption ecosystem, providing an accessible graphical environment for secure email and file protection. It packages the GnuPG engine together with user-friendly tools such as certificate management utilities, Windows Explorer integration, and Outlook plugins, enabling encryption workflows without requiring command-line expertise. The suite supports both OpenPGP and S/MIME standards, allowing organizations and individuals to secure... -
20
MCP Server Chart
A visualization mcp contains 25+ visual charts
mcp-server-chart is a TypeScript Model Context Protocol (MCP) server that turns AntV’s visualization stack into agent-callable tools for automatic chart generation and lightweight data analysis. Out of the box it exposes more than 20–25 chart generators—covering staples like bar, line, area, histogram and pie, plus advanced visuals such as dual-axes, heatmaps, radar, flow and fishbone diagrams—so an AI client can request a chart and receive an image URL in return. -
21
ShareX
Screen capture, file sharing and productivity tool
ShareX is a lightweight free and open source program that allows you to capture or record any area of your screen and share it with a single press of a key. ShareX offers numerous methods of capture including full screen, monitor, freehand and so much more. It also features plenty of customizable after-capture tasks and supports more than 80 different image, text, and file hosting services, as well as many URL shortening and sharing services. -
22
SingleFile
Web Extension for saving a copy of complete web page in a single file
...Wait until the page is fully loaded. Click on the SingleFile button in the extension toolbar to save the page. You can click again on the button to cancel the action when processing a page. Open the context menu by right-clicking the SingleFile button in the extension toolbar or on the webpage. It allows you to save the current tab, the selected content, the selected frame. With auto-save active, pages are automatically saved every time after being loaded (or before being unloaded if not). Right-click on the SingleFile button and select "Manage extension" (Firefox) / "Options" (Chrome) to open the options page. -
23
World Monitor
Real-time global intelligence dashboard
...Built primarily with TypeScript and modern web technologies, the project aims to reduce information fragmentation by consolidating hundreds of curated feeds into a single interactive environment. The platform emphasizes geospatial context through features such as interactive maps and a 3D WebGL globe, enabling users to visualize global events dynamically. It incorporates AI-assisted summarization and local LLM support to help users process large volumes of information more efficiently. The application can run as a native desktop app or progressive web app, reflecting a focus on accessibility and offline-capable intelligence workflows. ... -
24
C4-PlantUML
C4-PlantUML combines the benefits of PlantUML and the C4 model
C4-PlantUML combines the benefits of PlantUML and the C4 model for providing a simple way of describing and communicating software architectures – especially during up-front design sessions, with an intuitive language using open source and platform-independent tools. C4-PlantUML includes macros, stereotypes, and other goodies (like VSCode Snippets) for creating C4 diagrams with PlantUML. At the top of your C4 PlantUML .puml file, you need to include the C4_Context.puml, C4_Container.puml or... -
25
React & Redux in TypeScript
The complete guide to static typing in "React & Redux" apps
...It focuses on maintaining complete type safety while minimizing redundant annotations and manual type declarations. The guide explains React component types, hooks, events, context, higher-order components, and Redux-connected components. It demonstrates how type inference and control-flow analysis can keep application types concise and maintainable. Redux sections cover actions, reducers, selectors, asynchronous flows, middleware integrations, and store typing. A bundled playground project provides working examples that readers can clone and experiment with in a real TypeScript environment.
