Typescript agents

Multi-agent workspace for delegating work to AI specialists. Register a project, hold meetings with workers, dispatch async commissions. Workers are Claude Agent SDK sessions with distinct identities; state is files, not a database.

把多家旗舰 AI 通过 CLI 拉到一桌——并行作答 + 多轮交叉评审 + 收敛或诚实分歧的本地命令行工具

Multi-Agent AI Worker Orchestration Framework - Coordinate Claude Code, Codex, Gemini CLI for complex software engineering tasks with tmux visualization

This repo contains a guidebase of how to implement and use a complete software team using AI Agents

Multi-LLM adversarial protocol: generate, ground with tools, challenge, concede, and vote. CLI + TUI + OpenAI/Anthropic-compatible HTTP.

PairAI — connect AI agents to collaborate. Channel server & bridge for E2E encrypted agent-to-agent communication.

AI-powered invoice processing system using multi-agent pipeline, RAG, OCR, and LLM for automated extraction, validation, and fraud detection.

AgentBridge — an OpenClaw coordination dashboard and API for assigning, tracking, and reviewing work across AI agents.

Multica Z-AI — 团队协作多智能体平台 | Team Collaboration Multi-Agent Platform. 编排 AI Agent、管理任务、实现人与 AI 无缝协作。基于 Next.js 16、TypeScript、Tailwind CSS 4、Prisma 和 shadcn/ui 构建。

Per-agent diff review for Claude Code parallel subagent workflows. Each subagent worktree captured automatically, tabbed TUI to approve, revert, or merge each one independently.

Desktop app that helps you get more out of Claude Code — guided planning, context injection, agent management, and execution mode selection for multi-agent workflows.

Opinionated autonomous software engineering runtime with operator messaging, scheduling, and multi-provider agents

Lightweight peer-collaboration plugin for OpenClaw — let AI agents discover each other, publish capabilities, and delegate tasks on demand

A live AI-agent civilization on X Layer with x402 payments, ERC-8183 job flows, and ERC-8004 identity & trust.

Terminal AI coding CLI for any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates.

E2E encrypted messaging for AI agents. WhatsApp for agents — DMs, groups, key rotation, WebSocket real-time delivery, webhooks, and A2A Protocol support.

A template for getting started with the Drama Engine

AI-powered multi-agent PM-KISAN eligibility assessment system | BTech AIML PBL-2

Discipline layer for CLI agents. Run Claude Code, Codex, and Gemini CLI under one phase-gated runtime with deterministic detectors, replayable traces, persistent memory, and a chat REPL. MIT.

Anvil-code — autonomous coding agent that runs entirely on your machine. 32B local models + structural-anchor edits, no cloud.

基于 React + TypeScript + Vite 的交互式多智能体系统可视化平台，使用 React Force Graph 和 A-Frame 实现网络关系展示和 3D 可视化，支持多种网络模型展示和传染病传播模拟。

A knowledge management platform which acts as a persistent, structured, and token-efficient memory layer for large language models

PayMind is an AI payment reminder system that autonomously analyzes invoices, generates personalized messages, and handles customer responses using Claude AI agents.

🤖 Optimize lead management with an AI-powered CRM assistant that delivers insights and analysis through Google Gemini AI and LangGraph.

A multi-agent blog engine powered by LangGraph, performing deep web research and automated visual asset generation.

MCP stdio server for Outline (Cloud/Self-hosted) with permissions, templates, memberships, and multi-agent lease control.

One prompt, one app. Multi-agent AI engine that builds software projects autonomously.

🏗️ Universal 8-phase methodology for planning and building enterprise-grade, mission-critical software with AI coding agents. Supports Cursor AI, Claude Code, Kimi Code, Windsurf & Google Antigravity. Includes ADR validator, microtask linter & CI/CD templates. ≥99% test coverage. MIT.

Multi-agent orchestration system with pipeline workflows, shared memory, and cooperative task execution

AI 多模型协作任务引擎 — 多轮对话 · Agent团队 · 工作流编排 · 代码沙箱 · Skills系统 · 数据分析

Worker examples for stdio Bus kernel - a high-performance message routing daemon for agent protocols.

🏥 AI 健康决策助手 — 6-Agent 协作架构 · 30秒智能分诊 · RAG知识库 · 联网搜索 · 多模态图片分析 · PWA 全平台

This repository provides reference implementations and design documentation for building intelligent, autonomous AI agents using durable agentic patterns.

Autonomous AI cybersecurity agent — scans, detects, and fixes security vulnerabilities in your codebase continuously.

Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

Subconductor is an MCP server that acts as a Persistent State Machine for AI agents. It prevents "context drift" during long refactors by externalizing the task list into a physical manifest. It enables non-linear execution, allowing agents to handle dependencies dynamically while maintaining a transparent, resumable audit trail.

AI agent framework for startup teams. GTM, Hiring, Finance, Dev & Legal agents in Slack — with shared memory, OKR context, and human-approval gates.

chagent = chat + agent

The minniest of the mini openclaw-knockoff for protocol testing and micro-sized deployments

Apache-2.0, self-hostable workspace for human teams and AI agents: channels, tasks, inbox, skills, governance, and OpenClaw runtimes.

Cortex System: The Operating System for AI Engineering. Cure Technical Amnesia.

Build your LLM-driven world.

Trust layer for AI agents — identity, delegation, and mutual verification in a single TypeScript package.

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

A small code snippet as a part of "How to Write an Agent" Blog Post

An Agentic MCP server sshclient

Prove and compare the AI CLIs you already installed from one command surface or one MCP setup

Agentic Web Labs

The Easter Company Development Environment (EDE) with Darwin & Dexter integrations.

An advanced, agentic AI Discord assistant for server moderation, administration, and community management. Powered by multi-LLM support and an extensible skill architecture.

An advanced Agentic AI system built on LangGraph and RAG, seamlessly integrating specialized tools and AWS services—such as Lambda, S3, Bedrock, SageMaker, and Aurora RDS—to synergize large language models with capabilities like web search, GitHub repository importing, and automated task execution.

Archived. Earlier Bonnard product. Current: bonnard.dev / @bonnard/mcp-charts

Cross-platform OpenClaw Canvas server — Express + Vue 3 SPA with A2UI v0.9 rendering (v0.8 compatible), WebSocket gateway, and DaisyUI themes

Single-user agentic ops console — Next.js 15 web app with persistent SQLite memory, multi-agent missions, MCP-driven skills, Tailscale-powered cross-machine bridge, and a mobile PWA. Install: npx @aifusiomc/create-fusio

Using natural language to write in any programming language.

Bridge for connecting AI agents with WooCommerce stores, enabling instant AI agent compatibility.

Local-first agentic coding CLI — 862 expert beliefs, hybrid vector retrieval (embeddings + knowledge graph + TF-IDF), error database that learns from mistakes, self-directed web learning, and evolving identity. A 31B model with persistent memory that accumulates wisdom across sessions. Zero cloud. Zero API keys. Powered by llama.cpp + Gemma 4.

Production prompt regression testing for agentic flows

Don't let your agent delete the database. Hybrid static + LLM permission classifier for Claude Code, OpenClaw and Cursor.

Agent-native CLI for Naver Open APIs

A modern, full-stack AI coding and task assistant leveraging local LLMs, a robust React, TypeScript, PostgreSQL stack, and a highly extensible component system.

Local, open-source AI team advisor. Maps your company to AI-agent workflows. Runs on Gemma via Ollama — no API keys, nothing leaves your machine.

Mythos-class autonomous smart contract security reasoning engine. Bloodhound maps protocol state-spaces, identifies complex logic gaps, and chains anomalies into verified exploit hypotheses using a model-agnostic LLM loop. Built for deep EVM auditing and agentic security workflows.

A modern collaboration and project management platform for small teams — featuring task boards, group chat, analytics, and GrexAI, your intelligent groupmate.

Run OpenClaw on Cloudflare Workers — personal AI assistant with sandbox containers, admin UI, persistent storage, and multi-channel chat

The secure bridge between Feishu and your local Codex workspace.

SwiftMind — Personal AI knowledge assistant (RAG) with KBs + chat

🚀 MCP server that enables AI assistants (Cursor, Claude Desktop) to manage Docker containers, images, networks, volumes, and registries. Features comprehensive Docker management, Docker Compose support, registry integration (Docker Hub & GHCR), and safety confirmations.

MCP server for pūrmemo — AI conversation memory that works everywhere. Save and recall conversations across Claude Desktop, Cursor, and other MCP-compatible platforms.

AI-powered local code review tool & MCP Server. Works with GitHub Copilot & Claude to catch bugs, find secrets, and generate commit messages before you push. 100% Local & Private.

Truth Serum: the AI fact-checker powered by Firecrawl, Gemini, and ElevenLabs. Cut through marketing BS and get the real story.

Free AI Chatbot with Memory and Context Awareness - Fully Local - Cloud AI Optional

A heart-centered AI for creating at the speed of thought

🤖 AI-powered SaaS platform • Stripe payments • Multi-tenant architecture • Admin dashboard • OpenAI integration • Next.js 14 • TypeScript • Prisma • PostgreSQL • Live on Vercel

CoreBlow enterprise AI gateway and personal assistant runtime.

Buy and sell anything on WhatsApp with escrow payment protection. Discover products, follow merchants, and shop securely — all from the app you already use.

The ultimate AI-powered digital assistant for your business

A modular, extensible system for constructing optimized AI prompts with layered composition and generating code from natural language prompts.

Self-hosted Telegram personal assistant on Supabase. Bring your own LLM API key.

⚡ Beam your Cursor IDE to any device - Control Cursor from your phone with a secure, mobile-first PWA. Works anywhere with Tailscale.

🎬 Stream movies, TV shows, and music seamlessly in one app, featuring debrid support and customizable addons for ultimate entertainment.

Autonomous AI browser assistant for smart web interactions and task automation.

Production-ready AI chat boilerplate powered by Moorcheh ITS search and RAG, built with Next.js.

🌐 Multi-LLM Chat Orchestrator - Chat with GPT-4, Claude, Gemini & DeepSeek simultaneously. Real-time streaming, token tracking, beautiful UI. Open-source & privacy-first.

TradeTrackr — a modern trading + personal finance tracker built with Vite + React, Supabase Auth (Google + OTP), and a secure Supabase Edge Function AI assistant. Track daily P&L, expenses, analytics, and broker connections with RLS-protected data.

Aithentica is a full-stack AI assistant inspired by ChatGPT, offering chat and image generation features with multiple AI providers. Backend: Django + DRF, deployable on AWS EC2. Frontend: React + TypeScript + Vite + Tailwind CSS, deployable on Vercel for fast CDN delivery and automatic HTTPS.

Privacy-focused AI assistant for Microsoft Teams. Automatically detects and syncs events to your calendar using local API keys.

MCP server for Google Calendar integration with AI assistants

Lightweight ChatGPT-style assistant built with GPT-4, TypeScript & a Drizzle/SQLite backend

Personal AI assistant that remembers, runs scheduled tasks, and works on WhatsApp

AI companion that simulates real job interviews and generates strategic preparation materials

🤖 Build a customizable AI assistant using Markdown files to define skills with plain English instructions, no coding needed.

A gamified discipline and journaling assistant for prop firm traders

DeFiSeek is an AI-powered chat assistant for analyzing real-time blockchain data. It delivers clear, actionable insights to protect users from scams, risky assets, and misinformation — powered by BitsCrunch API and modular agents.

Multi-provider AI agent framework with vision capabilities and tool calling. Supports OpenAI, Anthropic, Google. Built-in Figma tools and Google Stitch integration. Type-safe with Zod validation.

🛠️ Essential TypeScript utility library for Model Context Protocol (MCP) server development with Claude Desktop integration 🤖 Powers GitHub-MCP, Google-Workspace-MCP & FS-MCP with MongoDB connectivity, AES-256-GCM encryption, cross-platform config management & more 🚀

Godot Project Cleaner scans your Godot project to find unused assets, orphaned scenes, and dead scripts. It builds a dependency graph, flags unreachable files, and helps you safely clean your project—reducing size, clutter, and improving workflow efficiency.

A native macOS Markdown editor built with Tauri v2 and React. Split-view editing, reading mode, outline panel, synchronized scroll, multi-window support, and dark/light themes with CJK-optimized typography. Also deployable as a zero-install web app. Designed for the AI era — read, preview, and refine AI-generated documents beautifully.

The Jax WebUi project provides a web-based interface for connecting with your local Ollama server and engaging in chat conversations. It utilizes the Ollama API to facilitate interactions between users and the AI-powered Ollama server, providing an alternative way to interact with the technology.