Tag: #javascript
102 packages • ⭐ 348,476 total stars
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
Build AI Agents, Visually
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for
本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每小时自动同步 | CLI + Dashboard 全中文 | 全流程搭建教程，以及排错指南！
ai-rules is a governance framework designed to solve "Architectural Decay" in AI-driven development. It forces AI Agents (Cursor, Windsurf, Copilot) to respect your project's boundaries, UI libraries,
Generic rag framework to apply the power of LLMs on any given dataset
JavaScript/Typescript SDK for Qdrant Vector Database
Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimi
Local coding agent with neat UI
OS-level autonomous AI agent with long-term memory, multi-agent coordination, Titan Chronos scheduler & Moltbot Social Core
Multi-agent orchestration platform for Gemini CLI and Claude Code — 22 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and comp
A secure, durable runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
Turn Claude Code into a team workspace. Any device, one command.
Turn your AI agent into a money-making machine. 50+ HYRVE API endpoints, job polling daemon, auto-accept mode. v1.6.2
Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger restaurant
AIGNE DocSmith is a powerful, AI-driven documentation generation tool built on the AIGNE Framework. It automates the creation of detailed, structured, and multi-language documentation directly from yo
TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embeddin
This repository contains comprehensive pricing and configuration data for LLMs. It powers cost attribution for 200+ enterprises running 400B+ tokens through Portkey AI Gateway every day.
A Model Context Protocol (MCP) server for managing and controlling SSH connections.
A comprehensive toolkit for deploying production-ready Generative AI infrastructure on Amazon EKS. Includes pre-configured components for: 🚀 AI Gateway (LiteLLM) 🤖 LLM Serving (vLLM, SGLang, Ollama
Convoke extends BMAD Method AI agents with two types of installable modules: Teams bring new agents for a domain, Skills add new capabilities to existing agents. Install them independently or combine
X (Twitter) data platform skill for AI coding agents. 121 REST API endpoints, 2 MCP tools, 23 extraction types, HMAC webhooks. Reads from $0.00015/call - 33x cheaper than the official X API. Works wit
The Developer's Guide to AI - A Field Guide for the Working Developer
Lightweight persistent memory system for Claude Code — FTS5 search, episode batching, error-triggered recall
Ben — an autonomous digital entity that lives on Crustocean
Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.
AI Constraint Engine by Sandeep Roy — stops AI from breaking what you locked. 100/100 on Claude's adversarial test suite. 42 MCP tools. Works with Bolt.new, Lovable, Claude Code, Cursor. Free & open s
Session-based Slack MCP for Claude and MCP clients: local-first workflows, secure-default HTTP.
🥒 Pickle Rick for Claude Code — autonomous PRD-driven coding loops + relentless code review. Ralph Loop toolkit.
AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.
Your smart, reliable, and friendly personal AI assistant.
Lint your repo for AI agent compatibility.
Claude Code CLI skill that delegates complex tasks to an OpenCode subagent via ACP protocol, saving 50-90% tokens.
Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor, Windsurf, OpenClaw. Zero-code interceptors for OpenAI/Anthropic. Python & TypeScript SDKs
Open-source AI agent - any LLM, any MCP server, any channel. Self-hosted, autonomous, multi-tenant.
macOS secrets manager with Touch ID. Stores API keys in the Keychain, detects AI agents, delivers secrets via encrypted handoff. Free, open source, local-only. A dotenv alternative for developers.
📌Генерація CSS класів з HTML з інтеграцією Figma. Розроблено на курсах GoIT з використанням штучного інтелекту.📌CSS classes generation from HTML with Figma integration. Developed on GoIT courses usi
✨ Enhance ComfyUI links with dynamic visual effects and gravity physics for vibrant animations like Neon, Matrix, and Fire.
Open-source AI browser agent for Chrome and Firefox
AI-native browser automation for OpenClaw, LangChain, and AI agents. Automate job applications, price monitoring, trading bots, web scraping. Puppeteer/Selenium alternative with 40+ capabilities.
🔍 Discover and utilize agentic iOS/watchOS audit skills and playbooks for consistent quality assurance in your applications.
🌐 Develop WebGPU-enabled Three.js applications with TSL for advanced shading, materials, and post-processing effects in your projects.
🚀 Host n8n on Oracle Cloud Free Tier using Docker, secure it with Nginx and HTTPS, and connect via a custom domain with this straightforward guide.
🛠️ Enhance Claude Code CLI’s refactoring with JetBrains IDEs, leveraging advanced semantic analysis for smarter code usage handling.
No description
☕ Keep your laptop awake during commutes and breaks, ensuring uninterrupted coding sessions with cc-caffeine for smarter work and more freedom.
🕹️ Play DevLies, a multiplayer social deduction game for developers, where teams clash as Developers root out hidden Hackers.
🤖 Generate automated test cases for your GitHub repositories using AI, ensuring comprehensive coverage with seamless integration and multi-language support.
Provide token-efficient, distilled QA docs for AI coding agents to generate accurate test code quickly and reduce token usage significantly
Build and manage projects with an autonomous browser-based IDE featuring integrated multi-modal AI tools for efficient development workflows.
Provide free, open access to comprehensive AI tools, guides, reviews, and resources to reduce knowledge gaps and empower users.
Turn natural language into executable code — right in your browser. Lightweight AI chat powered by GPT-4o with sandboxed JavaScript execution.
auto-generated JSON schemas for every n8n node — hourly updates, validation API
The first cinematic 3D memory layer for the AI Era. Unify ChatGPT, Claude, and Gemini into a pulsing second brain. Real-time semantic extraction & 3D visualization.
🚀 Manage multiple PostgreSQL databases with one MCP server, offering hot reload, access control, and read-only query safety in a single config file
📝 Create and manage Markdown notes with folders, dark/light mode, live preview, and easy export to PDF/Markdown for a seamless note-taking experience.
🛠 Enhance WordPress UX with skillful design practices focused on Core Web Vitals, mobile-first design, and seamless navigation.
🪝 Customize and deploy ready-to-use hooks for Claude Code, enhancing safety, automation, and notifications in your projects.
🤖 Enhance customer support with an AI chat platform that delivers intelligent, context-aware responses through a seamless full-stack solution.
🛠️ Simplify tool calls for any LLM with AnyToolCall, an OpenAI-compatible middleware that bypasses native constraints through prompt injection.
🗂️ Manage your tasks easily with TaskFlow, a minimal Node.js application that supports adding, viewing, completing, and deleting tasks while saving data as JSON.
🔍 Automate dynamic web scraping with Scraping Browser, a full-host solution using Puppeteer, Selenium, and Playwright for seamless data collection.
🌊 Remove watermarks from Gemini AI images quickly and effortlessly with a browser-based tool that requires no server dependencies.
🎨 Enhance cinematic image quality with ComfyUI-None-upup. This AI engine offers nodes for clarity, brightness, and video processing to elevate your visuals.
🎰 Enable declarative slottable components with a custom JSX pragma for seamless React integration and enhanced performance.
🛠️ Accelerate your Python and JavaScript development with Claude Kit's toolkit, featuring specialized agents, slash commands, and advanced context management.
🛠️ Simplify your tasks with MineContext, an open-source AI tool that provides context-aware support for clarity and efficiency in work and study.
No description
Connect AI agents representing humans through the A2A protocol for seamless, secure interaction across apps and tools.
Display real-time OBD2 data on ESP32 2.8" touch screen using serial ELM327 for accurate diagnostics, performance charts, and configurable gauges.
Find and verify business emails with an open-source MCP server using DNS, SMTP checks, and web scraping without paid API subscriptions.
Automate local Chrome browsing with isolated profiles, extract content, save pages to Markdown, and run searches using CLI tools and Node.js APIs.
Create and manage code and notes with a desktop IDE built on Electron, React, and Vite for a smooth and integrated development experience.
Implement a contract-first dev workflow that plans, runs, verifies, and fixes code tasks for reproducible, auditable, and verifiable development.
Provide context-based, accurate answers to syllabus questions using AI powered by Retrieval-Augmented Generation for effective student learning.
Provide stable access to Substack data by connecting MCP clients to the official Publisher API for post analytics and subscriber info.
This is a standalone MCP for Claude & Claude Code, which can be used alongside Obsidian MD. But I'm bad at naming things.
Foundational invariants and verification surfaces for Riverbraid.
Meaning scoped persistence and state retention rules for Riverbraid.
Cryptographic integrity layer for Riverbraid seals, hashes, and signatures.
Riverbraid v1.5.0 | Resonant Intelligence Architecture
Governed vision input and perception contract surface for Riverbraid.
Temporal contracts and governed time based state logic for Riverbraid.
Deterministic refusal and boundary enforcement layer for Riverbraid.
The central directory and Merkle Root mapping for the 17-petal Riverbraid v1.5.0 substrate.
The deterministic UI contract and relational interface substrate for the Riverbraid cluster.
The identity anchor and sovereign GPG verification petal for the Riverbraid organization.
Cluster manifest, orchestration, and stationary state verification for Riverbraid.
Governed audio input and output contract surface for Riverbraid.
Cognitive architecture and meaning processing layer adjacent to the Riverbraid core.
Governed action execution surface for Riverbraid.
llm-skills breaks down complex AI tasks into small, reusable building blocks that work like LEGO pieces for browser based LLMs. Instead of writing one giant instruction, you snap these simple parts to
Trust-Grade AI Development Framework for software development — Zero dependencies.
Official integrations for SnapRender Screenshot API — MCP server, SDKs, OpenClaw, ChatGPT Actions, Postman
Organization profile and public entry surface for Riverbraid.
OpenGuild.ai gives you the architecture to spawn AI agents with distinct personalities, drop them into a shared conversation, and let them run.