Search Results for "context" - Page 29
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 Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
1
rwkv.cpp
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
...RWKV is a novel large language model architecture, with the largest model in the family having 14B parameters. In contrast to Transformer with O(n^2) attention, RWKV requires only state from the previous step to calculate logits. This makes RWKV very CPU-friendly on large context lengths. -
2
AGiXT
AGiXT is a dynamic AI Automation Platform
AGiXT is a dynamic Artificial Intelligence Automation Platform engineered to orchestrate efficient AI instruction management and task execution across a multitude of providers. Our solution infuses adaptive memory handling with a broad spectrum of commands to enhance AI's understanding and responsiveness, leading to improved task completion. The platform's smart features, like Smart Instruct and Smart Chat, seamlessly integrate web search, planning strategies, and conversation continuity,... -
3
WALA
Libraries for Analysis, with frontends for Java, Android, and JS
The T. J. Watson Libraries for Analysis (WALA) provide static analysis capabilities for Java bytecode and related languages and for JavaScript. The system is licensed under the Eclipse Public License, which has been approved by the OSI (Open Source Initiative) as a fully certified open-source license. The initial WALA infrastructure was independently developed as part of the DOMO research project at the IBM T.J. Watson Research Center. In 2006, IBM donated the software to the community. The... -
4
rav1e
The fastest and safest AV1 encoder
rav1e is an open-source implementation of an encoder for the AV1 video codec, developed in Rust (with some assembly) by the community around Xiph Foundation. Its design philosophy is to start from a correct, minimal, and fast AV1 encoder — sacrificing some encoding speed/efficiency of reference encoders in exchange for simplicity, stability, and compilability across platforms — and then gradually improve. This makes rav1e particularly attractive for scenarios where you need AV1 encoding but... -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
Claude Code Tools
Practical productivity tools for Claude Code, Codex-CLI
...The project focuses on solving common problems encountered in AI-assisted development environments, including managing session history, automating terminal interactions, and maintaining context across multiple coding sessions. It includes tools that allow developers to search conversation logs quickly, manage environment variables securely, and execute interactive terminal workflows that AI agents can control. Some components enable Claude Code to interact with terminal multiplexers such as tmux so that it can run programs, debug applications, and interact with scripts that require user input. ... -
6
Anyquery
Query anything (GitHub, Notion, +40 more) with SQL and let LLMs
Anyquery is an open-source SQL query engine designed to allow users to query data from almost any source using a unified SQL interface. The system enables developers and analysts to run SQL queries on files, APIs, applications, and databases without needing separate connectors or query languages for each platform. Built on top of SQLite, the engine uses a plugin architecture that allows it to extend support to dozens of external services and data sources. Users can query structured files... -
7
Excalidraw MCP
Fast and streamable Excalidraw MCP App
Excalidraw-MCP is an open-source Model Context Protocol (MCP) application and server that connects the visual power of Excalidraw’s hand-drawn diagram editor with AI-driven workflows, enabling agents like Claude, ChatGPT, VS Code, and other MCP-compatible hosts to generate and manipulate diagrams programmatically. Rather than being just a static whiteboard, Excalidraw-MCP serves diagrams in real time using an MCP backend and streams interactive visual output back to the client, letting AI tools create shapes, connectors, text, and entire diagrams as part of conversational or task-based sessions. ... -
8
Pangolin
Identity-Aware Tunneled Reverse Proxy Server with Dashboard UI
Pangolin is an open-source, self-hosted tunneled reverse proxy server that brings identity-aware access control and dashboard management to exposing private services securely. It allows you to connect applications and resources behind firewalls or NATs to a central hub, using encrypted tunnels rather than opening public ports or relying entirely on VPNs. With Pangolin you can route traffic from across distributed networks, enforce contextual access rules (such as SSO, geolocation, time of... -
9
GLM-4-Voice
GLM-4-Voice | End-to-End Chinese-English Conversational Model
...GLM-4-Voice builds upon the bilingual strengths of the GLM architecture, supporting both Chinese and English, and is designed to handle long-form conversations with context retention. The repository provides model weights, inference demos, and setup instructions for deploying speech-enabled AI systems. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
10
RESTinio
HTTP/WebSocket server C++14 library
...Of course, you've got access to the structure of a given HTTP request, so you can apply complex logic for handling requests. Async request handling. Cannot get the response data immediately? That's ok, store the request handle somewhere and/or pass it to another execution context and get back to it when the data is ready. -
11
Qwen-2.5-VL
Qwen2.5-VL is the multimodal large language model series
...Trained on a comprehensive dataset of up to 18 trillion tokens, Qwen2.5 models exhibit significant improvements in instruction following, long-text generation (exceeding 8,000 tokens), and structured data comprehension, such as tables and JSON formats. They support context lengths up to 128,000 tokens and offer multilingual capabilities in over 29 languages, including Chinese, English, French, Spanish, and more. The models are open-source under the Apache 2.0 license, with resources and documentation available on platforms like Hugging Face and ModelScope. -
12
Eino
LLM application development framework for Go with agents and flows
...Eino includes an Agent Development Kit that enables developers to create intelligent agents capable of using tools, coordinating with other agents, and managing conversational context. Eino also offers orchestration capabilities that allow components to be connected into chains, graphs, or workflows for complex AI pipelines. These orchestration features handle concerns such as concurrency, streaming responses, and type safety so developers can focus on application logic. -
13
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer models. In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression... -
14
Weft
Task management, but AI agents do your tasks
Weft is an AI-augmented personal task management board where autonomous agents can be assigned tasks and then carry them out across real services like email, Google Docs, spreadsheets, GitHub issues, and pull requests. Instead of just listing to-dos, Weft lets users describe work and attach intelligent agents that read context, perform actions, and request approvals before committing state changes, making task execution partly automated without sacrificing control. It runs entirely on Cloudflare’s platform using Workers, Durable Objects, and Workflows, enabling scalable and persistent task state with minimal backend overhead. Users can set up parallel agents to handle multiple tasks at once and even schedule recurring jobs that trigger daily or weekly to keep workflows on track. ... -
15
Preguntas de entrevista para React
Questions about React for job interviews
Preguntas de entrevista para React is a comprehensive Spanish-language resource containing typical React interview questions organized from beginner to expert level. The repository is not just a list of questions: it includes detailed explanations in Spanish, making it useful as both an interview prep guide and a deeper learning reference.The content is structured in sections (beginner, intermediate, expert), covering everything from “What is React?” and JSX basics to advanced topics such as... -
16
LangExtract
A Python library for extracting structured information
...It is designed to transform free-form text into reliable, schema-constrained data while maintaining traceability back to the source material. Each extracted entity is precisely grounded in its original context, allowing visual inspection and validation via automatically generated interactive HTML visualizations. LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. The system excels at handling long documents using optimized chunking, multi-pass extraction, and parallel processing to ensure both high recall and structured consistency. -
17
Stremio Core
Types, addon system, UI models, core logic
Stremio Core is the Rust engine that powers Stremio’s apps by centralizing all reusable logic behind discovery, catalogs, metadata, streams, add-ons, and user/library state. It exposes a clean set of modules—types, addon_transport, and state_types—so apps can talk to add-ons, model UI state, and react to events without duplicating code. The architecture is inspired by Elm: immutable state, message-driven updates, and explicit side-effects (“effects”) keep behavior predictable and testable.... -
18
Hiring Without Whiteboards
Companies that don't have a broken hiring process
Hiring-without-whiteboards is a curated list of companies and teams that avoid traditional "whiteboard" interviews, instead focusing on realistic and practical evaluation methods. In this context, "whiteboards" symbolizes outdated or unhelpful computer science trivia questions often criticized in technical interviews. The project highlights organizations that emphasize interviewing techniques more aligned with actual day-to-day work, such as collaborative problem-solving, pair programming, or take-home assignments. It encourages a shift away from brainteasers, riddles, or puzzle-based interviews, which can create unnecessary barriers for candidates. ... -
19
Preact
Fast 3kB React alternative with the same modern API
...Its focus on size and speed makes it attractive for embedded widgets, mobile web, and scenarios where initial load must be extremely fast. The library embraces modern patterns like functional components, hooks, and context while keeping the API surface minimal. Tooling integrations and ecosystem packages round out the experience, so teams can ship production apps without sacrificing bundle budgets. -
20
Mem0
The Memory layer for AI Agents
...Key features include enhancing future conversations by building smarter AI that learns from every interaction, reducing LLM costs by up to 80% through intelligent data filtering, delivering more accurate and personalized AI outputs by leveraging historical context, and offering easy integration compatible with platforms like OpenAI and Claude. Mem0 is perfect for projects such as customer support, where chatbots remember past interactions to reduce repetition and speed up resolution times; personal AI companions that recall preferences and past conversations for more meaningful interactions; AI agents that learn from each interaction to become more personalized and effective over time. -
21
DevSpace
The Fastest Developer Tool for Kubernetes
...DevSpace is an open-source developer tool for Kubernetes that lets you develop and deploy cloud-native software faster. DevSpace is a very lightweight, client-only CLI tool which uses your current kube-context, just like kubectl or helm. It does not require you to install anything inside your cluster and works out of the box with every Kubernetes cluster. Builds all images in parallel using Docker, kaniko or any custom build commands (e.g. using cloud build). Tags images according to customizable tag schema and updates tags in manifests and Helm chart values. ... -
22
Vibe Coding CN
The ultimate workstation for turning ideas into reality
...It presents a workflow for turning ideas into working projects through structured AI pair programming. The methodology emphasizes planning, modular architecture, clear goals, strong context, and human review instead of uncontrolled AI generation. It covers project conception, technology selection, implementation, debugging, testing, and expansion. The repository also organizes prompts, reusable skills, project templates, tool recommendations, and configuration guidance. Its broader goal is to make AI coding workflows more systematic, maintainable, and reusable across development projects. -
23
Deep Agents
The batteries-included agent harness
Deep Agents is an open-source, batteries-included agent harness designed for long-running, multi-step AI work. It provides an opinionated agent setup while allowing developers to override or replace individual pieces without forking the project. The framework is model-agnostic and works with tool-calling models from hosted providers, open-weight deployments, or local runtimes. Built on LangGraph, it includes persistence, checkpointing, streaming, and production-oriented orchestration. Agents... -
24
mpai
Make Codex and Claude Code sessions multiplayer from the terminal
mpai is an open-source coordination layer that makes AI coding sessions collaborative directly from the terminal. It lets a named teammate enter an existing Codex or Claude Code conversation without switching tools or recreating its context. The host explicitly chooses which native sessions to share, while Tailscale provides the private device network. Teammates can follow live transcripts, switch sessions, show presence, and submit prompts with their identity attached. Viewer and participant roles, revocation, shared access rules, and an append-only audit trail help preserve owner control. ... -
25
MCP Agent Mail
Asynchronous coordination layer for AI coding agents
...It gives each agent a persistent identity, inbox, outbox, searchable history, and threaded Markdown conversations. Agents can send decisions, status updates, images, and attachments without relying on a human to relay context between parallel sessions. Advisory file reservations let an agent declare intended edits to files or patterns, reducing accidental overlap without enforcing rigid locks. Git stores human-auditable communication artifacts, while SQLite supports indexing, search, and operational queries. The HTTP-only FastMCP server works with clients such as Claude Code, Codex, Gemini CLI, and other MCP-compatible tools. ...
