Javascript agents

Turn your ChatGPT account into a local software factory. Four browser tabs plan, write, review and audit real projects, then install, run and screenshot them. No API key.

A cute desktop pet with a live Claude token usage meter - session & weekly rate limits in a thought cloud above your Windows taskbar. Free, open source, one-press install.

Skills Gallery — 1,672+ AI agent skills. One gallery. 60+ tools compatible. Install via npm, yarn, pnpm, bun, curl, pip, npx. By uthuman Inc.

Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.

AI 原生 3D 恋爱养成游戏 | 对你的爱，超越空间

🎓 AI-Powered Timetable Generation System for Educational Institutions | Genetic Algorithms | React + Node.js + MongoDB | Real-time Analytics | Gemini AI Chatbot

Claude Code plugin (Agent Skill) for BPMN 2.0 - read, explain, create & edit .bpmn process diagrams with clean auto-generated layout, validation, and control-flow linting (deadlocks, stuck tokens). Works with Camunda Modeler & bpmn.io.

Generate custom Solana vanity addresses on demand from your agent.

Turn any AI agent into an interactive tutor over Model Context Protocol — lessons, quizzes, feedback.

Push notifications and alerts AI agents can send and manage.

Harmovela Protocol: open coordination protocol for autonomous systems — event, task, state, delegation, recovery, and governance.

This project demonstrates how to build a generative AI chatbot on AWS using AppSync, Lambda, DynamoDB, Amazon Bedrock, and Terraform.

PaperCraft — From idea to accepted paper at top CS conferences. 17 rules + 12 skills that guide CS researchers through the full research pipeline.

Keep GPT and DeepSeek conversations continuous in Codex Desktop, allowing the two models to work alternately within the same project. 在 Codex 桌面应用中实现 GPT 与 Deepseek 任务上下文双向交接，让两个模型在同一个项目下交替工作。

Marblo — the live orchestrator for AI-native teams

Run AI agents in the Polkadot app. E2E-encrypted and private.

A powerful starting point for creating a feature-rich Discord bot that utilizes modern slash commands.

A multi-agent AI brainstorming platform — assemble a team of customizable AI personas that discuss, debate, and ideate with you.

Public Preview: self-hosted, protocol-first AI gateway and agent control plane for OpenAI, Anthropic, Gemini, MCP and A2A — governed tools, prompt enhancement, virtual-key budgets, cache and audit; zero-key first run.

Korean stock market data for AI - KOSPI/KOSDAQ closing prices and DART disclosures as free JSON, plus an MCP server. No signup, no API key.

sap abap ai agent cli

让 DeepSeek Harness(dsh) 在 HarmonyOS 完整跑起来：缓存优化对话预设 + 启动补丁 + 工具链 | Run DeepSeek Harness on HarmonyOS: cache-optimized agent presets, patches & tooling

A visual multi-agent workspace for DeepSeek Harness (DSH) Web.

Claude Code records what you work on into Jira, Linear, GitHub Issues, Trello or Vikunja, automatically

Generalized implementation of IdleRPG, a game which rewards participants for remaining idle.

Superpowers (obra/superpowers) as a DeepSeek Harness plugin: the methodology skills plus their session bootstrap

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness — strict evidence, health-checked failover, original pixels, and Token accounting.

Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation

A UNIX-philosophy Agent application for macOS.

Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.

An Agent-First Repository is a human-governed software environment designed so AI agents can execute engineering work efficiently while deterministic controls constrain their authority, verify their output, and preserve human accountability.

Metodología y copiloto agéntico de diseño de producto. Expande el pensamiento divergente en 8 etapas auditables con memoria persistente resiliente (SQLite/MCP), autoaprendizaje y detección temprana de alertas y sesgos. Mapea contratos vivos y asegura un handover técnico riguroso.

Codex integration plugin for DeepSeek Harness, providing native Codex conversations powered by the Codex App Server, with workspace, terminal, approval, and DSH tool support.

TradingView Premium × Claude MCP setup — drive your own TradingView Desktop session via Chrome DevTools Protocol for chart analysis, signals, and backtesting from Claude Code. Analysis only, no order execution.

Markup and iterate your projects live with your agent.

Open-source, self-hosted alternative to Airtable, Fibery, Notion databases and ClickUp: a database and work management platform built for AI agents, agent-first (Claude Code, Codex, Cursor, any MCP client). Tables, relations, formulas, rollups, workflows, markdown/PDF documents, one SQLite file. REST, CLI, MCP server. Zero dependencies, MIT.

Model orchestrator: rules, subagents and a lane runner tell agents which model to use, so small work goes to cheap tiers and fewer tokens go to frontier models.

AI agents and skills for mobile development: Flutter, Android, iOS and React Native. Plugin for Claude Code and Codex.

中国软著登记材料生成器：源码进去，页数一页不差的 PDF 出来

Git 提交一键转禅道任务：自动汇总需求、按 T1~T7 难度阶梯定工时、日期铺排与任务闭环，生成经得起审计的工时汇报。AI Agent 技能包，支持 Gitea/GitHub/Gitee，MIT 开源。

Local-first Windows desktop workspace for Codex, OpenCode, Cursor Agent, GitHub Copilot, Gemini CLI, and other AI coding agents.

An Roleplay AI client run directly inside Cloudflare Worker that support multiple feature, polished from backend to frontend.

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

Multi-agent AI orchestration platform — coordinate, observe, and govern autonomous agents

The first MCP server for Guesty property management. 38 tools for reservations, guests, messaging, pricing, financials, calendars, reviews, tasks, webhooks, and more. Connect AI agents to your Guesty account.

MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution

Your personal Claude Code agent, running 24/7 in the cloud. Talk to Claude from Telegram, Discord, or the web — with memory, tools, and automation.

Autonomous perpetual futures trading skill for OpenClaw AI agents on Aster DEX

MCP server giving Claude live access to SAP systems via ADT — read, edit, search, test, and diff ABAP across landscapes without installing anything on the SAP stack.

Your agent docs lie. Nerviq finds the lies in 30 seconds — stale references, permission exposure, and cross-platform drift in CLAUDE.md / AGENTS.md / Cursor rules. Deterministic, zero dependencies, MIT.

CLI for EmblemAI Agent Wallet — manage crypto across 7 chains without seed phrases

Full Stack ChatGPT

A2A protocol bridge plugin for OpenClaw — agent card, JSON-RPC endpoint, and remote agent tools

MCP server that generates Draw.io diagrams from natural language — supports flowcharts, sequence diagrams, ERDs, and network diagrams

Chrome extension + multi-agent LLM pipeline that bypasses Zhihu's anti-scraping defenses to profile any public user across PII leakage, content authenticity, and HEXACO personality. 绕过知乎反爬，浏览器扩展 + LLM 多智能体生成用户深度画像。

This is a repository for the Crew AI agents with full stack development using JS(Basic).

Build E2E Micro SaaS AI application, takes in Github urls, generate json reports with AI powered insights and repo stats

A quick and lightweight library to chat with databases. It uses schema over bulky data embedding for efficient and speedy interaction, ensuring data security.

A modern web application that integrates a conversational AI chatbot with real-time user interactions smooth animations. Built using React, Framer Motion, Lucide Icons, and ShadCN Components on frontend and fastapi on backend. [Below is website deployed Frontend]

A powerful web-based research assistant built with Node.js that leverages Ollama LLM to generate intelligent search queries and fetch comprehensive results from popular search APIs (Tavily, Perplexity, or DuckDuckGo). Based on Ollama Deep Researcher from Langchain.

Thalia🍃 currently not developing any more.

AI-powered health & nutrition app offering personalized care, meal plans, baby tracking, pregnancy support, and smart hospital location services.

PulsarWave: An ML and NLP-powered tool for highlighting key trends/insight in news feeds data.

LangForge is a comprehensive documentation platform for LangChain and its ecosystem, providing detailed guides, API references, and interactive examples for building with large language models (LLMs).

Cognifold is sci-fi inspired interface to aggregate various specialized AI agents, making them easily accessible and manageable right from your desktop.

ai-auto-crawler: puppeteer + autogen

🎵 Voice-enabled context engineering system for Claude Code with accessibility features and documentation-to-development bridge

Sysclone: A purist, dependency-free Universal Interpreter and JIT compiler built entirely in JavaScript. Currently executing MS-DOS QBasic with absolute fidelity.

A lightweight and flexible JavaScript library for creating and managing workflows and agents.

A modern, responsive web-based chat interface for nanoclaw.

A Chrome extension that allows you to input your question once and have an answer from multiple AI services at once.

🌐 Enhance OpenClaw with this Chinese translation, auto-syncing official updates within one hour for Windows, macOS, and Linux users.

AI-powered browser automation agent using a dual-LLM architecture. The orchestrator (qwen3-vl-32k) creates execution plans from screenshots, while the executor (llama3.1:8b) translates steps into browser actions using an accessibility tree for reliable element selection. Local, private, powered by Ollama.

The Doctor Recommendation System is an intelligent healthcare platform designed to help patients find the most suitable doctors based on their medical needs, location, specialization, and availability. This system leverages modern technology to bridge the gap between patients and healthcare providers, ensuring quick and reliable.

Stuck While Coding? CoderClue Can Help You Out. CoderClue is Built Using OpenAI and It is very useful in day to day life of a programmer.

A modern, feature-rich SSH terminal application built with Electron and React. KEMENT combines traditional SSH functionality with AI-powered assistance to enhance productivity and streamline remote server management.

🤖 AI-powered chat specializing in explaining, refactoring, debugging and converting short code snippets.

AI-powered assistant that listens to your calls and provides intelligent, knowledge-based answers — completely invisible to screen sharing.

Claude Code handoffs that preserve decisions, failed approaches, constraints & next steps

🤖 AI-powered Microsoft Word Add-in — Integrates Claude AI for smart writing, document analysis, Track Changes, and specialized legal tools.

Universal document-to-markdown and section splitter for HTML, URLs, and PDFs.

One-click conversion of arXiv papers to Markdown with perfect LaTeX formula preservation

Open source AI inference server with Model Marketplace, Document RAG, and OpenAI-compatible API

AI-powered Web3 chat that mixes live market and DeFi data (CoinGecko, DeFiLlama) with RAG over a PostgreSQL/pgvector knowledge base; React + Vite frontend and Express backend.

A tutorial-scale, fully local RAG-based chatbot built with Gemma 3 via Ollama + Bright Data SERP API + Chroma. This researches topics comprehensively and then answers questions using retrieval-augmented generation.

A comprehensive AI-powered study assistant that transforms your PDF study materials into interactive learning tools including flashcards, practice exams, and an intelligent chat interface powered by Google Gemini AI.

Portable vector database with auto-installing Ollama embeddings. Zero-config semantic search via SQLite.

A basic project for RAG with Node.js

Practical AI & more workflows for coding, MCP, local AI, productivity, research, media, and ops.

A demo chatting with documents scanned with Dynamic Web TWAIN

Seamlessly integrate NotebookLM with your AI agent using the Model Context Protocol (MCP). Includes detailed setup, authentication guides, and automated installation skills

Bridge to run Codex CLI as a Claude Code native teammate — multi-model agent orchestration for AI-powered development

Structured document annotations with REST API + MCP. Replace Google Docs commenting with agent-consumable feedback.

Prompt to Animation — turn a text description into a downloadable interactive character bundle.

Self-improving AI agents that run 24/7 on Claude Code. Discord, Telegram, Slack. One command setup.

Forge Plugin: Zero-dependency governance for Claude Code. 21 commands, 22 agents, 29 skills.

Adversarial, Multi-Agent Career Knowledge Base & Resume Pipeline

A robust, local-first intelligence application for scraping and analyzing Dark Web data.