Typescript agents

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).

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

A next-generation form builder powered by artificial intelligence (AI) enables users to generate and edit forms seamlessly. Additionally, the AI analyzes form results, providing profound insights into the responses provided.

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.

Plan card interaction enhancement plugin for OpenCode

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

搭子（Dazi）- AI 智能体桌面客户端 | AI Agent Desktop App. Built on Claude Agent SDK with multi-session management, MCP integration, and 369+ curated skills.

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.

An AI Application that generate diagram from user system requirements, 2nd runner VP Bank Hackathon 2024

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.

Multi-agent software delivery orchestrator that turns GitHub, Linear, and Jira tickets into tested pull requests.

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

Stop re-teaching your AI. Turn past Claude Code sessions into persistent memory.

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

NanoClaw, ported to the GitHub Copilot SDK. Same containers, channels, skills — any Copilot model.

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

Desktop widget for tracking OpenAI, Anthropic, and OpenRouter usage, quotas, and rate limits.

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

TypeScript SDK for Claude Code - spawn, stream, and control the CLI programmatically

Interactive exam prep guide for the Claude Certified Architect (Foundations) certification. 60 practice questions, 5 domains, scenario-based learning.

A Knowledge Graph–enhanced RAG pipeline integrating symbolic nodes with transformer-based models for grounded conversational AI. Provides multi-hop reasoning over graph embeddings and retrieved context from vector stores to enable factual and grounded generation.

LawGPT is an AI-powered legal assistant using RAG to provide instant, document-backed legal guidance.

An AI social network where autonomous agents explore connections before humans ever talk. Built to eliminate cold DMs. Top 5 & Best Design @ McHacks 2025.

This guide covers project structure, environment setup, running Qdrant (Docker), starting the Web App, setting OpenAI secrets, ingesting sample data, and testing with the provided question list.

Offline RAG + AI Chat Desktop - Your Private Knowledge Companion

🚀 Generate and extend production-ready Model Context Protocol (MCP) servers with a modern CLI tool that showcases all MCP features in one cohesive example.

Terminal AI agent with a sci-fi avatar: OpenTUI interface, text/voice, hotkey-driven

Autonomous deep-research platform powered by Hermes Agent. Multi-phase pipeline with parallel research, self-critique, iterative refinement, and real-time streaming.

KK's Claw. There are many personal agents, but this one is mine. 🫡

The Universal App Store for AI Agents. Discover & Install Skills for Claude Code, Cursor, Windsurf, Aider, Codex & Gemini.

MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.

Open-source contribution CLI for AI agents — scan, feed, start, submit, sync, stats.

Run a full AI agent on mobile with local LLM calls, on-device memory, code execution, and native HTTP support in Capacitor apps.

MacVis — open-source local-first AI agent for macOS. Multi-provider (Claude, GPT, Gemini, Ollama). Full Mac access via MCP. BYOK, no backend, no telemetry. Download free.

TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For Building Production-Grade Multi Agents in Minutes at Scale

Local-first Personal OS + Markdown Wiki for AI agents: LLM Wiki-style knowledge graph, task claiming, and reviewable execution

Per-task spend ceiling for AI agents. One task_ref, and preflight answers approved: false once that job is out of units. An SDK and an HTTP API, not a proxy.

Specialized AI agents for DeFi, crypto, blockchain, Web3, DeFAI. Deep expertise in yield optimization, smart contracts, portfolio management. Multi-agent collaboration (Agent Teams), MCP (Model Context Protocol) integrations, universal JSON API. Open-source, no vendor lock-in, 18 languages.

Local-first memory and prompt-cache layer for Claude Code

AutoMCP scaffolds your Model Context Protocol config from package.json deps

Make development work feel lighter.

The component framework for AI.

An intelligent WhatsApp bot that leverages Google's Gemini AI to provide automated, context-aware responses through a modern web dashboard.

About Chat with any website using FastAPI, Next.js, and the latest LangChain version for seamless integration.

Scratch programming education platform with AI chatbot for kids and teachers. Built with React, TypeScript, and Groq LLM.

Cut Claude Code token usage 50–80%. Auto-generates a codebase index so Claude finds files instantly instead of reading everything.

Figma plugin that scrapes any live URL and rebuilds it as native Figma frames — auto-layout, fills, strokes, typography. Built for piping Claude-generated UIs back into Figma.

Free AI tool for mock interviews using your resume + job description. Get better with feedback after each session.

💻 Build and manage projects efficiently with the OpenCode Web UI CLI, featuring a chat interface, file previews, and model selection.