Search Results for "context" - Page 15
Sort By:
Showing 1921 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.
-
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
Roarr
JSON logger for Node.js and browser
JSON logger for Node.js and browser. A transport in most logging libraries is something that runs in-process to perform some operation with the finalized log line. For example, a transport might send the log line to a standard syslog server after processing the log line and reformatting it. Roarr does not support in-process transports because Node processes are single threaded processes (ignoring some technical details). Given this restriction, Roarr purposefully offloads handling of the... -
2
Ulixee Hero
The web browser built for scraping
It's the first modern headless browsers designed specifically for scraping instead of just automated testing. Hero provides access to the W3C DOM specification without the need for Puppeteer's complicated evaluate callbacks and multi-context switching. We've recreated a fully compliant DOM directly in NodeJS allowing you bypass the headaches of previous scraper tools. The powerful Chrome engine sits under the hood, allowing for lightning fast rendering. Emulators make it easy to disguise your script as practically any browser. -
3
ripgrep
Regex pattern directory search tool that respects your .gitignore
ripgrep is a line-oriented search tool that actively searches the directory you're currently in for a regex pattern. By default, ripgrep will ignore your .gitignore and skip hidden files or directories and binary files automatically. ripgrep has first class support on Windows, macOS and Linux, with binary downloads available for every release. ripgrep is similar to other popular search tools like The Silver Searcher, ack and grep. ripgrep supports arbitrary input preprocessing filters which... -
4
Xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models
...Unlike traditional 3D parallel training strategies, XTuner introduces optimized parallelism techniques that simplify scaling and reduce system complexity when training massive models. The engine supports training models with hundreds of billions of parameters and enables long-context training with sequence lengths reaching tens of thousands of tokens. Its architecture incorporates memory-efficient optimizations that allow researchers to train large models even when computational resources are limited. XTuner is also designed to integrate with modern AI ecosystems, supporting multimodal training, reinforcement learning optimization, and instruction tuning pipelines. -
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.
-
5
DBHub
Universal database MCP server connecting to MySQL, PostgreSQL
DBHub is a universal database gateway that implements the MCP server interface so assistants and IDEs can explore and query databases through typed tools. It supports multiple transports—stdio for desktop clients and HTTP for networked scenarios—making it flexible to embed or deploy. Configuration is environment-variable driven, with a DSN and per-engine settings covering Postgres, MySQL, MariaDB, SQL Server, and SQLite. Operational flags include read-only mode, row limits, and even SSH... -
6
MaxKB
Open-source platform for building enterprise-grade agents
MaxKB (Max Knowledge Brain) is an open-source platform for building enterprise-grade AI agents with strong knowledge retrieval, RAG pipelines, and workflow orchestration. It focuses on practical deployments such as customer support, internal knowledge bases, research assistants, and education, bundling tools for data ingestion, chunking, embedding, retrieval, and answer synthesis. The system exposes flexible tool-use (including MCP), supports multi-model backends, and provides dashboards for... -
7
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. ... -
8
TraceRoot
Find the Root Cause in Your Code's Trace
...Human-in-the-loop interaction is central: developers can guide reasoning by selecting relevant spans or logs, then verify agent reasoning through traceable context. -
9
Destructive Command Guard
The Destructive Command Guard (dcg) is for blocking dangerous git
...It intercepts shell commands before execution and blocks operations that could erase files, rewrite Git history, destroy infrastructure, or remove data. The Rust implementation uses fast filtering and context-aware rules to distinguish dangerous execution from harmless text matches. Its modular security packs cover Git, filesystems, databases, containers, cloud platforms, Kubernetes, Terraform, and other tools. Users can inspect denials, enable agent-specific profiles, add allowlist entries, or temporarily bypass a rule when necessary. ... -
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
Ellama
Ellama is a tool for interacting with large language models from Emacs
...It supports conversational interactions, code assistance, and text transformation tasks, making it useful for both programming and writing scenarios. Ellama integrates with existing Emacs buffers, allowing users to send selected text or entire documents as context for AI operations. It also supports multiple providers, including Ollama, enabling local-first usage without relying on external APIs. -
11
LLM Wiki
Open Source Implementation of Karpathy's LLM Wiki
...It allows users to create interconnected knowledge bases that function similarly to a wiki but are enhanced with AI-driven content generation and summarization. The system emphasizes linking and context, enabling information to be connected across pages and topics for better navigation and understanding. It likely includes features for automatic content updates, ensuring that information remains relevant as new data becomes available. The architecture supports both manual editing and automated generation, providing flexibility in how knowledge is curated. ... -
12
Rust Port
The Rust workspace under rust/ is the current systems-language port
...It is often used as a sandbox for exploring how large-scale coding agents behave, including their decision-making processes, tool usage, and workflow orchestration. The system likely includes abstractions for handling file systems, executing commands, and maintaining context across sessions, allowing for more persistent and intelligent coding interactions. -
13
RAG Web UI
RAG Web UI is an intelligent dialogue system based on RAG
RAG Web UI is an open-source intelligent dialogue system built on retrieval-augmented generation technology, designed to enable users to create AI-powered question answering systems grounded in their own knowledge bases. It combines document retrieval with large language models to provide accurate, context-aware responses based on indexed data rather than generic model knowledge. The platform supports ingestion of multiple document formats, including PDFs, Word files, Markdown, and plain text, automatically processing and vectorizing them for efficient retrieval. It features a multi-turn conversational interface that maintains context across interactions, allowing users to engage in more natural and continuous dialogues with their data. ... -
14
ReMe
Memory Management Kit for Agents
ReMe is a memory management kit for AI agents that gives them structured, persistent memory capabilities, enabling agents to extract, store, and reuse information across sessions, tasks, and interactions. It is designed to support long-running agent workflows where context matters and working memory alone isn’t enough, helping agents remember user preferences, task histories, and relevant past observations. The toolkit provides APIs to offload large, ephemeral outputs to external storage and reload them on demand, which reduces memory bloat and keeps active context concise. By combining embeddings, vector search, and summarization workflows, ReMe lets developers build agent systems that can recall and apply past knowledge in future reasoning tasks. ... -
15
Qwen3-ASR
Qwen3-ASR is an open-source series of ASR models
...As a specialized ASR variant of the broader Qwen language model ecosystem, it focuses on capturing reliable transcriptions from audio sources such as recordings, live streams, or conversational inputs while supporting low latency use cases. The architecture combines advanced neural acoustic modeling with context-aware language prediction so that outputs maintain both fidelity to the original speech and grammatical coherence. This makes Qwen3-ASR suitable for voice-driven applications like AI assistants, dictation tools, speech analytics pipelines, and accessibility features, where accurate and fluid transcription is critical. -
16
PPTAgent
PPTAgent: Generating and Evaluating Presentations
PPTAgent is a research system for generating and evaluating slide decks that goes beyond simple text-to-slides. It follows a two-stage, edit-based workflow: first it analyzes reference presentations to infer slide roles and structure, then it drafts an outline and iteratively performs editing actions to produce new slides. The project includes both the generation agent and an evaluation framework, PPTEval, to score content quality, design, and coherence. The repository highlights the EMNLP... -
17
Dunst
Lightweight and customizable notification daemon
Dunst is a lightweight replacement for the notification daemons provided by most desktop environments. It’s very customizable, isn’t dependent on any toolkits, and therefore fits into those window manager-centric setups we all love to customize to perfection. Customize fonts, icons, timeouts, and more. Are you unhappy with the default shortcuts and colors? No worries, you can change these all with a simple configuration file tweak. Change the look or behavior of notifications matching a... -
18
Qwen3-VL
Qwen3-VL, the multimodal large language model series by Alibaba Cloud
...The model supports dense and Mixture-of-Experts (MoE) architectures, making it scalable from edge devices to cloud deployments, and is available in both instruction-tuned and reasoning-enhanced variants. Qwen3-VL is built for complex tasks such as GUI automation, multimodal coding (converting images or videos into HTML, CSS, JS, or Draw.io diagrams), long-context reasoning with support up to 1M tokens, and comprehensive video understanding. It also brings advanced perception capabilities, including spatial grounding, object recognition, OCR across 32 languages, and robust handling of challenging inputs like low-light or distorted text. -
19
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
...It combines image and text inputs into a unified embedding / reasoning space so that you can query with text and image jointly (e.g. “What’s going on in this scene?” or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). ... -
20
PrivateGPT
Interact with your documents using the power of GPT
PrivateGPT is a production-ready, privacy-first AI system that allows querying of uploaded documents using LLMs, operating completely offline in your own environment. It provides contextual generative AI capabilities without sending data externally. Now maintained under Zylon.ai with enterprise deployment options (air gapped, cloud, or on-prem). -
21
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. ... -
22
Claude Code Best V3
The original Claude Code is runnable and buildable
...It operates primarily in terminal or IDE environments, where it can analyze code, explain logic, and perform actions such as refactoring, debugging, and managing version control. The system is designed to understand the structure and intent of a codebase, allowing it to provide context-aware assistance rather than generic suggestions. It supports plugin-based extensions that enhance its capabilities with specialized commands and workflows. The architecture emphasizes productivity, enabling developers to offload routine tasks and focus on higher-level problem-solving. It also integrates with existing development tools, making it adaptable to different workflows and environments. -
23
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. -
24
OpenCTI
Open Cyber Threat Intelligence Platform
...It provides a modern web application backed by a GraphQL API and a data model aligned with the STIX2 standard to ensure interoperability across the threat intelligence ecosystem. The platform enables teams to correlate technical indicators such as observables and TTPs with higher-level context like attribution and victimology, creating a unified intelligence knowledge base. OpenCTI is built to integrate with external tools including MISP, TheHive, and MITRE ATT&CK, allowing it to function as a central intelligence hub in security operations. Its design emphasizes traceability by linking intelligence objects back to their original sources and tracking confidence levels and temporal metadata. -
25
STORM
An LLM-powered knowledge curation system that researches topics
STORM is an open-source virtual assistant framework developed by Stanford's OVAL lab. It is designed for creating natural language interfaces and assistants that can interact with APIs, databases, and services in a modular way.
