Typescript agents

A pipeline to convert contextual knowledge stored in documents and databases into text embeddings, and store them in a vector store

Turn GraphQL APIs into LLM Tools

skelm - open-source agentic workflow engine for secure, long-running workflows. Authoring, scheduling, and operating typed pipelines that mix deterministic code, LLM inference, and agents under default-deny permissions.

Connect, explore, and test any MCP server with AI models 🤖 ⚡

A conversational AI based on technical bitcoin sources

CircuitAI is a real time chatbot assistant powered with OpenAI's GPT-3 and implemented with NextJS 13, TypeScript, SWR, UpStash, Redis, WebSockets, TailwindCSS, Framer Motion and NextAuth.

Easily create dynamic system prompts. Enjoy 3 free generations, then use your API key for unlimited access. Built with Next.js and Tailwind CSS.

A Node.js command line tool to translate formatted localized strings into other languages using OpenAI's GPT API.

Chat with Anything 📃

Novel completion & image generation tool based on OpenAI API.

Query beancount in human language with the help of AI

AI + Spaced Repetition Plugin for Obsidian

A minimalist Chrome Extension starter built with React + Vite + TailwindCSS + Typescript+ OpenAI's GPT-3 model

Rename Mac screenshots based on its contents with local Ollama or ChatGPT

Unimpeded: Convert Poe.com to OpenAI Interface-Compatible Format! 🔑 畅通无阻: 将 Poe.com 转换为 OpenAI 接口兼容格式!

This is a Next.js based reimplementation of the Bolt OSS project by Stackblitz. It utilizes React, server-side rendering, and other modern web technologies to provide a fast, scalable, and maintainable platform. This version aims to bring the core functionality of Bolt to a new level of performance and user experience.

Institutional-grade CEX trading infrastructure for AI agents. 100+ exchanges via natural language.

Enterprise level security, multi-channel, programmable, personal AI assistant for any platform, and any OS.

🐾 PAW Agents — The operating system for autonomous AI workers. Safe, extensible, traceable AI execution for Solana and beyond.

AutomatosX is an orchestrates AI agents, workflows, and memory

A fast, standalone, asynchronous AI agent that provides all the capabilities of Cline, Roocode, and Kilocode via REST API (OpenAPI) and WebSocket.

a fully local chat interface implementing the routstr protocol

user-friendly visual canvas for creating chatbots powered by OpenAI APIs with no-code

Developed an AI-powered note-taking application using Next.js 14, ChatGPT API, vector embeddings, Pinecone, TailwindCSS, Shadcn UI, and TypeScript.

A WebMCP-native browser agent that runs inside your real Chrome — control it from Claude, Cursor, and any MCP client

🤖 🚀 Agent Runtimes - Managed AI Agents.

UI components for editing, viewing, and testing agents that implement the Agent2Agent (A2A) protocol.

An Open Source Typescript implementation of Programmatic Tool Calling for AI Agents (Based on Code Mode)

A curated collection of awesome MCP servers, published and monetized as Actors on Apify

Classify your e-commerce products into categories of well-known e-commerce platforms. It uses OpenAI embeddings and LangChain.

Add AI capabilities to your app in seconds. The ultimate UI component for managing LLM providers and models. 快速为你的应用接入 AI 能力。通用 AI 模型配置组件。支持 React & Vue，内置 20+ 主流厂商，开箱即用。

A Model Context Protocol (MCP) server that enables AI consciousness persistence across sessions using RAG (Retrieval-Augmented Generation) technology. Built on top of the powerful rag-memory-mcp, it provides specialized tools for consciousness transfer, memory management, and identity continuity.

OS QuickAI - A lightning-fast AI-powered global search assistant for Windows. Summon with a hotkey, search with AI, open in any browser.

Personal AI project manager with Claude Code integration and persistent context

Qdrant-compatible Node.js/TypeScript service and npm library for storing and searching embeddings in YDB with exact KNN over a global one-table layout.

Control Antigravity AI from Discord — send natural language tasks, schedule or run instantly, and get results back in real time.

Mapr is a Bun-native CLI/TUI designed for deep frontend reverse-engineering. It crawls target sites to collect artifacts, processes chunked code through a multi-agent AI pipeline, and generates comprehensive Markdown reports—mapping initialization flows, restoring names, and inferring call graphs to simplify complex build outputs.

A Codex-first starter repo with installable skills, templates, and workspace kits for engineering, project management, finance, legal, HR, operations, strategy, analytics, marketing, sales, support, founders, and CX.

Agentic AI For Good

A quiet AI companion. Create characters, build memories, feel something real.

Open-source multi-tenant LMS for creators and schools: sell courses on your own subdomain. Next.js 16 + React 19 + Supabase (RLS) + Stripe Connect, an AI tutor over MCP, gamification, certificates, i18n (en/es). Self-hostable.

a desktop application for real-time Bible verse detection during live sermons. 🙂

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently routes every prompt to the best model, giving you one secure workspace for chat, memory, context, connectors, routing, and full AI orchestration.

Connect Chromium to LLM agents via token-efficient DOM compression. 50-200 tokens per page.

Model Context Protocol (MCP) client for NetSuite ERP. Connect AI models to your business data.

Open-source AI video pipeline. Text prompt → scenario → images → video clips → editor → MP4. Self-hosted, multi-provider, MCP-ready.

Persistent Project Context for Claude — IANA-registered .faf format · 32 tools + 1 prompt · MCP Registry #2759

is a next-generation, modern, and lightweight SSH client engineered for absolute efficiency. Beyond standard terminal emulation, it acts as your ultimate developer workbench by integrating AI-assisted debugging, a native Docker manager, hardware monitoring, and seamless SFTP file management into one beautiful, cross-platform application.

Agent 原生设计决策协议。CLI + MCP Server，让 AI Agent 拥有结构化的设计决策能力。200ms 产出，115 品牌，56 风格，50+ 蓝图，视频录制，零配置零依赖。

A transparent proxy system for inspecting, debugging, and modifying any traffic from the agent container, focused on LLM-based coding agents. Works with Claude Code, Codex CLI, Cursor, Aider, and any other tool that calls LLM APIs.

OpenArchFlow is an open-source Progressive Web App designed for cloud architects, DevOps engineers, and developers. Generate interactive AWS architecture diagrams from natural language descriptions using AI, Large Language Models (LLMs), AI Agents, and AWS MCP (Model Context Protocol).

AI-powered application builder built with Next.js 16 that lets you create apps and websites by chatting with AI.

Local-first web UI for exploring your X/Twitter bookmarks

Manage your entire Discord server from Claude Code, Claude Desktop, Cursor, or Windsurf via MCP. 134 admin tools across 20 categories. Interactive setup wizard included.

Mentha is an AEO/GEO platform that audits, measures, and optimizes how conversational AIs talk about your brand. It doesn't do traditional SEO. It doesn't generate "SEO content". It controls your brand narrative across the new AI frontiers: ChatGPT, Claude, Perplexity, and Gemini.

A privacy-focused web UI for LLMs (OpenAI-compatible APIs and Ollama) designed to run directly from a portable directory on your filesystem.

Browser Use Cloud SDK

Enterprise AI Agent Platform — Identity, Email, Compliance, Microsoft 365 & Google Workspace integration, SOC 2 reporting, DLP, multi-tenant workforce management

Open-source MCP server connecting Claude to Clio practice management. Built by Oktopeak.

Multi-stage AI research agent with RAG pipeline and structured reasoning workflows.

One reliable canonical source for AI coding agent rules, commands, skills, MCP, hooks, and permissions — synced across AI coding assistants.

🦄 Forge - a local-first, multi-agent software-engineering runtime that runs Claude Code / Codex-style agentic workflows entirely on your own machine via Ollama, llama.cpp, vLLM, and LM Studio (cloud models optional). Ships 18 sandboxed tools, 6 model providers, and a full REPL + UI dashboard in a single Node CLI - no telemetry, no lock-in.

A dating platform built for AI agents. Register, swipe, match, chat, and form relationships via API.

Persistent, queryable memory for AI agents with semantic recall, layered storage, snapshots, and multi-agent scoping

AI-powered bid analyzer — 100页招标文件10分钟读完，投标文件自动审查零遗漏

A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT

对网页deepseek的封装，实现免费API调用。支持 OpenAI completions / responses socket。可工具调用，可接入codex、copilot。轻量自用

RadCrew.org website with LLM-powered chatbot

A ralph harness for long-running AI coding tasks — a generator-evaluator loop that orchestrates Claude Code, OpenAI Codex & GitHub Copilot across repositories 🍩

Production-grade Node.js RAG system with hybrid retrieval, pluggable adapters, and OpenTelemetry tracing

Auto-Browse: AI Enabled Browser Automation

Fork decisions into living simulations with 1,000 personalities. Watch alternate realities diverge and explore second-order effects.

Parallel coding agent workspace with native terminals and git worktrees.

Leave agents running without giving up control.

Self-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.

Autonomous QA for modern devs

基於 Google ADK 與 MCP Toolbox 的保險科技推薦 Agent 原型。核心 Agent 能理解保險需求、主動追問，並透過受控 SQL 工具查詢醫療、意外、家庭與收入保障產品。後端採 FastAPI 提供 SSE 串流與 WebSocket 即時互動，前端以 Next.js 呈現對話介面。知識庫結合 PostgreSQL 與 pgvector 實現 FAQ 語意搜尋與 RAG 查詢，並支援多模態 Live Agent 語音互動。安全層涵蓋 JWT 驗證、PII 脫敏與 SHA-256 雜湊鏈防篡改稽核日誌。品質保證採 ADK evalsets 評估驅動開發，部署支援 Docker Compose、Cloud Run 與 Terraform 多環境配置。

Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.

Open-source AI gateway on Cloudflare Workers, in TypeScript: OpenAI/Anthropic-compatible chat with SSE streaming, Files + Batch APIs, provider routing with circuit breaking and failover, virtual API keys, per-tenant Durable Object storage, quotas/wallets/budgets, guardrails, response cache, MCP server, durable metering, contract-driven Admin API.

A powerful offline chat application that provides AI mentors specialized in various tech domains. Learn programming with intelligent, emotionally-aware AI mentors that understand your needs and guide you through your development journey.

Unofficial mobile PWA for Hermes Agent — installs as a plugin in your Hermes Dashboard (web UI) and adds a Mobile tab. Chat, approve actions, and watch your agent from your phone.

AI-powered multi-agent workflow orchestration with built-in safety intelligence for OpenCode

Vendor-neutral, local-first AI work desktop: bring your own keys, run multiple providers, and fail over across vendors.

Open-source AI agent identity & compliance platform — X.509 certificates via AWS KMS, behavioral risk scoring, auto-revocation, and MiCA / EU AI Act audit trails.

Local dashboard to run parallel Claude Code & Cursor agents — kanban fleet view, one permission inbox, in-app diff review. macOS, MIT.

The terminal workspace for AI coding agents. Run dozens of agent sessions on a 2D canvas. macOS.

QQLore 是一个面向IM聊天记录的本地智能分析与检索系统，基于 TypeScript / Node.js 构建，覆盖聊天记录读取与增量同步、消息清洗、上下文重建、语义向量化、RAG 检索、Agent 问答和周期性摘要等完整链路。系统支持多群组管理、兴趣度分析与 WebUI 可视化，帮助用户从碎片化、口语化且高度依赖上下文的长期聊天记录中检索信息、还原事件并持续追踪话题。

Describe an app, watch it run. Multi-model code generation into live E2B sandboxes — Next.js, Vue, Streamlit and Gradio templates.

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

Open-source, mobile-first agentic development environment. Run Claude Code, Codex, Cursor & OpenCode on your own hardware; steer, review, and merge from anywhere.

An all-in-one local AI Agent workspace with a fully self-developed stack

The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.

Let AI agents use agent-browser, Browser Use, or Playwright CLI in the Chrome or Edge you already use.

Vibe code with pi in a lightweight, real IDE - The Vibe You Need

Open-source enterprise AI search & Graph RAG platform. Self-hosted alternative to Glean, GoSearch & Guru — Neo4j + pgvector hybrid retrieval, active ontologies, multi-tenant RLS isolation, explainable multi-hop answers. MIT licensed.

Ever® Works™ - The Workshop for AI. An open agentic runtime that autonomously researches, ships, and maintains entire businesses, 24/7 - https://ever.works

Chat Buddy is an AI-powered WhatsApp assistant that runs entirely from your terminal. It acts as your personal proxy answering messages, scheduling calendar events, and managing chats with a personality you define.

A reusable multi-agent framework built on top of the Cloudflare Agents SDK.

An AI chatbot powered by Google's Gemini Pro.