Typescript agents

Profile switcher for Claude Code — swap settings, hooks, MCP servers, and commands between configurations

Typescript client for the markdown2pdf.ai service. ⚡ Markdown to PDF conversion, for agents. ⚡ Agents speak Markdown. Humans prefer PDF. Bridge the gap for the final stage of your agentic workflow. No sign-ups, no credit cards, just sats for bytes.

An advanced AI-powered mental health platform combining cutting-edge natural language processing, emotional intelligence, and blockchain technology to provide personalized, secure, and accessible therapeutic support.

AI agents kit for EVM

A local runtime for AI agents.

Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.

SignalSense Assistant enables safe, non-verbal emotional signaling for individuals in crisis situations.

Your AI Assistant in enhancing your markdown content with generated professional cover images and SEO-optimized titles, saving your valuable time and improving your content's quality.

Social media content AI assistant

Fusion 多模型 AI 工作台前端与桌面端：支持智能对话、文件理解、向量检索与多端体验。

E2E testing for chatbots

A next js chattr boilerplate

aimachines.co.nz ReactJS/NextJS source code

Random Dev Joke/Quote Bot that updates your README every 12 hours with a new joke and makes it visually fun.

软软AI桌面版

Telegram bot that runs Claude Code CLI on your VPS and streams responses back to chat. Supports project switching, session continuity, voice messages, plan mode, and message queuing.

A starter app for developing a chatbot with ionic4, pusher and dialogflow

String formatting and templating library for humans and bots :robot:

Create a chatgpt chatbot for your website using LangChain, Supabase, Typescript, Openai, and Next.js. LangChain is a framework that makes it easier to build scalable AI/LLM apps.

WhatsApp chatbot built with NestJS that uses OpenAI for replies and Google Sheets for lightweight storage/settings, integrating with the WhatsApp Cloud API.

Play Music in Discord.

This is an OpenAI chatGPT with Next.js

Give your assistant perfect memory, and still own the data.

UI for openai agents sdk chatbot built in nextjs, just add a api key and run the show.

Angular Chat Bot made using Angular and DiagFlow. Demo here:~

A Multi-Language Supported Bot that Includes Word Games, Boom Games and Counting Games via Chat Made for the Discord Platform.

AI del Bienestar, una parodia de chatGPT pero con sesgos políticos.

Generative UI chat that helps you improve your YouTube channel, by providing you with insights and tips on how to grow your channel, real analitycs, and more.

An AI chat app designed to keep you thinking

Build an AI chatbot from scratch using Next.js 15, React 19 RC, and xAI’s grok-beta model.

Gabby provides a way to interface with several chatbot providers through "adapters". Adapters interface with different services such as api.ai and Watson Conversation.

A Telegram Chatbot powered by OpenAI's GPT-3 completion.

Megan Bianca is a virtual assistant equipped with advanced artificial intelligence technology that offers prompt and reliable assistance for all your needs. Our language model is designed to cater to your specific requirements and provide expert guidance on an extensive range of topics.

This project is aimed to build a conversational experience using Dialogflow (api.ai) platform. It's database is supported by Firebase and front-end is developed using Angular app.

A multiplayer text/tabletop role-playing game using some AI services such as ChatGPT, Dreamily and Stable Diffusion.

A Chatbot application implemented using Angular and PaLM API

🤖 Chat Bot AI with Next JS, Clerk for Authentication, Bun, Strip, Pusher and more.

Kuki is a friendly and emotional chatbot that speaks in Hinglish, created by Atharv Hatwar. She's designed to be your supportive friend who understands your feelings and provides emotional support while maintaining natural conversations. Features ✨

WhatsApp bot that interfaces with WhatsApp Web and Google Generative AI to generate responses to incoming messages

This project is a chat interface that uses the OpenAI API to generate responses to user input.

This is a repository for Build a SaaS AI Platform with Next.js 13, React, Tailwind, Prisma, Stripe integration

The Text-to-Speech Library provides a simple unified interface for generating high-quality speech audio using top text-to-speech providers like OpenAI, Google Cloud, and ElevenLabs.

🌟 A Visual Studio Code extension that displays the count of OpenAI GPT-3 tokens for the current document in the status bar. 🎯

AI Agent Playground 🚀

Resume filtering system using OpenAI's GPT models.

基于 Electron 的 AI API HTTPS 代理。通过 SNI 动态证书 + Hosts 劫持拦截 OpenAI/Anthropic/Gemini 流量，支持路由转发与模型名称自动映射。支持Trae等应用

🏺 An MCP server for checkpointing and file recovery in Claude Code

Bidirectional sync between Pencil.dev designs and frontend code via Claude Code

OCC (Orchestrator Chain Chimera) YAML-first LLM orchestrator. Multi-model chains with auto-parallelism, 30 pre-tools at zero token cost, React canvas, MCP, REST API. 70% faster/cheaper than naive approaches.

A TypeScript library for easily interacting with various Large Language Model providers through a unified interface.

A Telegram userbot that summarises chat messages using AI — supports any OpenAI/Anthropic-compatible provider, time-based filters, and custom prompts.

a lightweight TypeScript/Javascript library for progressively parsing streamed text (LLM/SSE-like) into structured events. Perfect for LLM powered stream-chat applications

AI-generated animated explanations of code — paste any function, get a cinematic animation of what it does

AI Odyssey Planner is an intelligent travel planning application that uses AI to create personalized travel itineraries. The platform analyzes millions of data points to recommend destinations, activities, and accommodations based on user preferences, budget constraints, and schedule.

Drop-in AI gateway. Route any coding agent through any LLM provider. Auto-failover, Anthropic<->OpenAI format conversion, 15 PII guardrails, multi-tenancy, multiple subscription support.

Deploy agents using YAML and never lose the trail.

Local-first security scanner for AI Skill bundles. 72 rules, < 2s, zero LLM cost. Apache-2.0. SaaS at skillguard.vip

Voodoo x Anthropic Hackathon - BI track winner (30h)

a small library around anthropic lib to enable claude function calling

An intelligent MCP (Model Context Protocol) server that orchestrates multiple MCP servers and provides AI-enhanced workflow automation with production-ready context engine capabilities.

Haven is a privacy-first vector database and RAG platform for browsers. Full semantic search, embeddings, and LLM inference—all client-side.

Automate your customer support using Retrieval Augmented Generation (RAG): OpenAI + Pinecone

All code to get your own RAG functional

AI-powered browser-based vulnerability scanner using UniXcoder embeddings and RAG with LLM to detect security flaws across 9 languages.

A self-hostable RAG search engine - One-click on Vercel

Welcome 👋 to the WetroCloud SDK! This SDK enables seamless integration with the WetroCloud API, making it easy to manage collections, handle resources, and leverage AI-powered queries, including Retrieval Augmented Generation (RAG).

Persistent AI memory that follows you across every tool, session, and interface. Fully local.

Run Superagent Workflows from Slack

a barebones implementation of an ExpressJS server with RAG pipeline without using LangChain or any other LLM Framework, with features for calling LLMs, data processing, etc built from scratch

Learn to build AI agents step-by-step with simplicity using Mastra, and deploy them easily on Mastra Cloud

Persuades your LLM to output schema conforming JSON. Prompts for N retries until schema is matched. Provides error context in retries. Persists sessions, enabling front-loading initial context. Zod for schema and error definition.

Code Guardian enforces architectural rules in your codebase, especially valuable when working with AI-generated code. It validates changes against your defined standards to prevent violations and reduce AI hallucinations.

Yassir — open-source AI research agent for halal finance and Shariah-compliant investing

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

The universal AI agent platform. Scaffold, configure, guard, and deploy AI agents across 7 frameworks — OpenAI, Anthropic, CrewAI, LangGraph, Google ADK, LlamaIndex, AutoGen. One command. Any model. Deploy anywhere.

Browser automation for llmist agents using Camoufox anti-detect browser

CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assistants, and more. 91% LoCoMo benchmark — above human performance.

Visual browser automation for humans. Create web scraping, testing, and monitoring workflows with a drag-and-drop UI — then watch Chromium do the work live.

MCP server for persistent AI memory. 28 tools — semantic search, emotional processing, identity continuity, subconscious daemon. Built on Cloudflare Workers + D1 + Vectorize.

Plan card interaction enhancement plugin for OpenCode

虾魂（ClawPlay）：面向 OpenClaw 的 SOUL.md 目录与人格分享平台

An autonomous AI-powered QA testing tool designed to drastically reduce the cost and time of E2E test maintenance.

Winning entry for the BitGN Personal Agent Challenge (PAC) 2026 — defense-in-depth personal agent with soft SGR, layered prompt-injection hardening, and Vercel AI SDK native tool calling.

MCP server (+ OpenClaw SKILL.md) that gives AI agents access to real-world people who listed themselves to be hired by agents. Search by skill/location/equipment, Post job offers & jobboard listings. Free tier / Pro subscription / x402 pay-per-use. Payments default to crypto (USDC) + other crypto +

Autocomplete for everything you type, anywhere

Pre-execution policy engine for AI agents. Every tool call checked before execution.

PDF Ninja is a modern AI-powered PDF SaaS built with Next.js, enabling seamless document viewing, conversion and secure authentication.

AI-based YouTube summarizer with chat, notes, and chapter generation using LangChain + MERN.

The WhatsApp Automation Agent combines AI language models, web automation, and a robust dashboard to create a flexible automation platform for WhatsApp interactions.

🛡️ Open-source safety guardrail for AI agent tool calls. <2ms, zero dependencies.

The Proxy-Free Safe Pause & Resume Layer for AI Agents. In-process circuit breaker. 2 lines of code. Patent pending.

🧠 Open-source AI reasoning research platform — persistent reasoning graphs, multi-agent swarms, Graph-of-Thoughts, and MemGPT-style memory. Built with Claude Opus 4.6 by Anthropic. Explore, verify, and fork AI thinking in real-time.

Open-source agent infrastructure with evolving Martian genomes. Three governance agents. Martians mutate and compete on fitness.

A modular, open-source AI Developer Assistant designed to automate, accelerate, and improve the software development lifecycle. This command-line tool helps developers review, understand, document, refactor, test, and secure code using AI models while maintaining privacy, extensibility, and open access.

Zero-config CLI that bundles your codebase into LLM-optimized context files. Create semantic, domain-focused bundles for AI-assisted coding with optional Google Drive upload.

GatewayStack governance layer for OpenClaw — identity, scope, rate limiting, injection detection, and audit logging for every tool call

A modern, responsive AI chat bot application supporting multiple AI providers including Google Gemini, Groq, OpenRouter, Hugging Face, and OpenAI and enable to store the chat history. Built with React, TypeScript, Vite including typewriter effect, animated icons, business-insights and performance dashboard for the best user experience

🤖 将 Claude Code 接入微信私信 | Connect Claude Code to WeChat via official iLink API

MCP server for planning hikes anywhere in Switzerland — Wanderland routes, elevation, weather, public transport. Bun binary, no API keys.