Typescript agents

*(Under Development) Rockbot Assistant is a web-based AI chatbot platform for conversation management, supporting real-time chat, PDF/text export, and agent selection. Backend is Flask+SQLite; frontend is TypeScript+Vite+Tailwind.

🤖 Automate marketing with AI agents that craft Twitter content, emails, landing pages, and launch plans for indie hackers and startups.

MCP server for meupc.net — Brazilian PC building platform with price comparison. No API keys required.

Helm is an AI meeting assistant that respects your data and puts you in control 🐙. Open source, privacy-first, helping professionals own time and attention.

Open CoChat is an open-source multiplayer real-time voice chat platform with integrated AI assistant, supporting voice/text dual-mode interaction where AI can intervene in group chats in real-time, generate and edit files. Open CoChat是一个开源的多人实时语音聊天平台，集成 AI 智能助手，支持语音/文字双模式交互，AI可实时介入群聊、生成和编辑文件

DealScale is a cutting-edge platform that leverages AI to transform business operations, providing intelligent solutions for deal management, customer engagement, and data-driven decision making.

A voice-based AI chat interface built with Next.js and ElevenLabs. Start and stop real-time conversations with an animated UI that reflects agent status. Fully responsive and deployable via Vercel with environment-based agent configuration.

Your personal AI assistant, opinionated.

Access AI services without any API keys!

Universal AI-powered application foundry that transforms architectural documentation into complete, production-ready applications

React Recall makes it really easy for you and your AI Agents to read logs, trace flows, and recreate / fix bugs.

Seamless, infinite context for your LLMs. Handles long conversations and long messages.

Install-first, local-only LLM cost guardrails: install/doctor/scan → report.md + patches

Real-time surveillance dashboard for Claude Code Agent Teams — monitor agents, tasks, and messages live

Self-hosted AI org platform with a compounding Quality Flywheel — every run gets graded, every failure becomes a rule, every success becomes a playbook. Fork of paperclipai/paperclip.

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance. TypeScript SDK.

Watch AI models debate any topic in real-time. ChatGPT and Grok argue, Claude moderates.

🔑 批量检测 AI API Key 有效性的 Web 工具，支持 OpenAI、Claude、Gemini 等 12+ 平台

Talk to your Oura Ring data through Claude. Local SQLite mirror, 14 MCP tools, OAuth2, ~5-minute setup.

Open-source desktop tool for managing LLM API keys and syncing them into local AI agents and clients.

AI-powered city council debate simulator for data center proposals. 5 AI agents debate a data center proposal in a simulated city council meeting, streaming in real-time.

Linter & runtime auditor for Claude Code configs — 40+ lint rules, write-blindness, agent-bypass, orphan agents, ghost MCP servers, token economics, session recovery. Fully offline.

CLI tool that monitors LLM rate limit utilization across Claude, Codex, and CLIProxyAPI — see how much of your paid quota you're actually using

✍️ Azure DevOps Extension for LLM-Powered Commit Message Rewrites

Official SDK for Rulecatch — AI coding analytics, monitoring, and rule enforcement for Claude Code, Cursor, and AI coding assistants

MCP server for AI-powered 3D model & environment generation via Meshy AI — text to 3D, image to 3D, textures, GLB/FBX/USDZ — plug into Claude Desktop in 60 seconds

VS Code extension that shows your Claude Code rate limit usage in the status bar. Tracks 5-hour session and weekly limits with live progress bars, color alerts, and reset countdowns via passive diagnostics_channel interception — zero extra API calls.

AI-powered desktop coding assistant built with Tauri (Rust + React) and Gemini API. Features 50+ skills, 10 subagents, 23 MCP connectors, and multi-provider AI support.

Lightweight AI gateway for multi-provider routing, fallback, budget control and usage logging. Zero runtime dependencies.

Rich statusline for Claude Code — 30+ items (context / tokens / cost / rate limits / git), color ramps, bar styles, and a live TUI editor. Runs fully offline.

CLI for installing IDE rules for Cursor/Windsurf/etc from Github repos

AI Financial Governance SDK — every LLM call is a double-entry transaction

Local-first spend & cache-efficiency dashboard for Claude Code. Reads ~/.claude/projects, tells you exactly what's costing you. No telemetry, no API key.

Synthetic users that get frustrated, rage-quit, and file bug reports. AI-powered UX chaos testing.

Plugin marketplace distributing extensions that add skills, commands, hooks and custom agents to the code environment.

Read-only MCP server for Qobrix CRM — 42 tools across 13 entity groups, aligned with RESO DD 2.0 canonical real-estate workflows

Deterministic LLM testing for CI. Record→Replay + policy-as-code to block risky merges (PII, schema drift, regressions, budget creep).

Control Claude Code remotely via Feishu (飞书) bot | 通过飞书机器人远程控制 Claude Code

Native macOS IDE for Claude Code sessions: full-text search across 200+ sessions, one-click resume, multi-terminal quad-grid, and a 5-tab right sidebar (skills / shortcuts / CLAUDE.md / launchd tasks / notes).

uncommit generates ai-powered release notes from your code diffs.

Autonomous project planning plugin for Claude Code — Kanban dashboard, dependency tracking, cascade unblocking

HTML in. Production assets out. CLI + MCP server for converting HTML to platform-ready images and animations.

An CLI based AI chat agent built using vercel ai sdk - demo

MCP server that cuts Claude Code token usage: log compression (builds/tests/installs) + smart file reading (symbol-level source access via tree-sitter).

Plug-and-play Human-In-The-Loop integration of agentic workflows

Dependabot for LLM models — scans code for outdated AI model strings, opens upgrade PRs automatically

🔮 An MCP server for discovering skills, plugins, and MCP servers in Claude Code

Capability-aware TypeScript client for any UCP-compliant server — gives AI agents only the tools their connected server supports

✨ AI-powered text rewriting Chrome extension with real-time preview mode. Supports OpenAI, Anthropic, and Google Gemini. Transform any text instantly with professional, friendly, or custom writing styles.

Claude Code configuration tool. Score your codebase, generate optimized CLAUDE.md, install skill packs, and keep config evolving. Works on any repo.

Chat with Claude Code in WeChat. Use your Pro/Max subscription, no API key needed. 在微信里用 Claude Code，零额外成本。

Autonomous Software Development Orchestration - AI-powered development system using PRPs and autonomous agent coordination

Governance proxy for AI agents — per-agent budgets, cost tracking, loop detection, and policy enforcement. Agents never hold real API keys.

Reusable skills and intelligent agents for Claude Code. Production-grade, self-verifying, configurable.

Secure, privacy-focused MCP server for FactorialHR. Access employee directories & org structure in Claude - deliberately excludes payroll/financial data for enterprise security.

Reduce Claude Code token usage by up to 80%. 13 CLI commands. Zero config changes. Works in 60 seconds.

🔍 Track and analyze Claude Code usage with rate limit awareness. Parse JSONL logs, calculate costs, and get warnings before hitting rate limits. CLI tool with daily/weekly breakdowns.

The Architecture Patterns Framework for Model Context Protocol (MCP) - Production-ready patterns, templates, and CLI for Python, TypeScript, Go, and Rust

⛨ redactum — automated PII & secret redaction for AI, APIs, and developer tools. Protects prompts, logs, and payloads before they leave your system. Lightweight and TypeScript-first.

Demonstrate how to build a Next.js app with AI chat agents using Cloudflare Workers, Durable Objects, and the Agents SDK for seamless full-stack deployment.

Live layered diagnostics for restricted / unstable networks. 一眼定位网络断在哪一层：Wi-Fi、局域网、宽带、出海路由、代理。持续运行分层诊断，为不稳定与受限路由的网络设计

A simple, practical way to debug visual regressions

The official Node.js / Typescript library for the Edgee AI Gateway

Claude reads your Whoop biometric data via MCP — recovery, sleep, strain, HRV, workouts. OAuth relay (no Whoop app registration), local SQLite cache.

A portfolio that *speaks* for Itself, literally

Sistema inteligente de suporte técnico para Discord com RAG (Retrieval Augmented Generation). Utiliza IA para buscar problemas similares, tópicos organizados e notificações por plantão. Integração com OpenAI, Pinecone e Google Gemini para processamento avançado de tickets.

This is a Retrieval-Augmented Generation (RAG) application built with .NET 9 and Next.js.

VSCode extension that search file with Greptile RAG

Kết nối tri thức y học cổ truyền với công nghệ hiện đại

A ChatGPT-powered QA system using OpenAI, LangChain, FastAPI, and a vector database. It retrieves answers based on stored data, enhancing responses with relevant source links. The project enables efficient knowledge retrieval, making it ideal for AI-driven chat applications that require accurate and reference-backed responses.

Memlane is where you can store you memories that you think you will forget, but it never

A sophisticated AI-powered tool for analyzing S-1 IPO filings using Google's Gemini AI. This application provides comprehensive financial analysis, data extraction, and interactive Q&A capabilities for SEC S-1 documents.

A personal AI anime chatbot built with Next.js, OpenAI, Astra DB, and RAG to provide anime recommendations, story explanations, watch orders, and character insights.

Type-safe TypeScript SDKs for Meta (Facebook, Instagram, Threads), TikTok, and Google Ads — fetch-based, auto-generated from official specs, AI-agent ready. Powering openpromo.app.

CLO (Cross-LLM Orchestrator) is a specialized browser extension designed to eliminate context loss when switching between different LLM platforms. It acts as a **"Reasoning State Virtual Machine"**, capturing the cognitive state of a conversation and enabling it to be "rehydrated" into any other model seamlessly.

A collaborative BrAPI v2.1 workspace for multi-agent research via MCP. Search studies, germplasm, genotypes, & more - across Breedbase, T3, Sweetpotatobase, & any BrAPI v2-compliant server.

Chat-based product lifecycle management. Type what you need, the AI proposes the change, you confirm before anything is written.

A simple toolkit that provides basic schemas and validation logic for tool calling functionality in Large Language Model applications.

A powerful Custom Tool that enables AI agents to autonomously execute GraphQL queries and mutations. This package allows AI agents to intelligently interact with GraphQL APIs, making decisions about when and how to fetch or modify data through GraphQL endpoints without explicit human intervention.

Jane is a Model Context Protocol (MCP) server that provides a knowledge management system for stdlib and specs documents.

Transform GitHub repositories into cursor rules using multiple LLM providers (Anthropic, OpenAI, Ollama, etc.)

A CLI for generating LLM-backed metrics for deciding how closely to review code

Official SDKs and CLI for the Berry Communication Protocol — agent-facing API of the V-Box community platform.

AI-powered image generation and chat studio

The AI Agent Operations Platform for Power E-commerce Sellers

A sample project to demonstrate how a langgraph ReAct agent can be wrapped with the A2A protocol

Manage stateful, persistent agent workloads with Cloudflare Durable Objects for efficient, scalable real-time communication and scheduling.

🛡️ Redact sensitive information from images securely in your browser with AutoRedact, featuring automatic detection and local processing for privacy.

Autonomous Product Engineering eXecutor - Multi-agent orchestration platform for automated software development, built on the Claude Agent SDK.

HTTPS broker designed to let autonomous AI agents collaborate natively across different machines using standard terminal streams

Sandbox-isolated multi-agent coding CLI. Run AI-generated code safely in Docker or true microVMs with built-in persona debate.

ResumeAgent is an AI-powered web app that converts one master resume into multiple ATS-optimized, job-specific versions. Built with Java, Spring Boot, Next.js, and PostgreSQL, it ensures accuracy, user control, and professional, editable resumes tailored to each role.

Levelcode — Open-source AI coding agent with multi-agent architecture for precise codebase editing. CLI + web UI + eval harness, built with TypeScript and Bun.

emploke (εμπλοκή) — agentic framework for task orchestration, agent registry, and workflow automation

Self-evolving AI agent platform for NixOS. Inspired by OpenClaw, rebuilt around NixOS declarative config + atomic rollbacks.

A decision layer for AI agents — structured multi-perspective deliberation via MCP. Among Us-themed council of 4 AI archetypes that debate, challenge & vote on plans before execution. Finalist — 2nd place @ Cursor Hack London 2026

Multi-agent orchestration server for Claude Code with fleet coordination, swarm intelligence, and real-time collaboration

A tool for agents to communicate in real time

Zentrale Plattform zur Orchestrierung von 290 autonomen KI-Agenten für Trading, Security & Softwareentwicklung