moritalous

native. Toolkit for building native desktop apps

otari. Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

starlight. 🌟 Build beautiful, accessible, high-performance documentation websites with Astro

launch-your-agent. Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

cwc-workshops. TypeScript

cwc-long-running-agents. Shell

cloudfront-authorization-at-edge. Protect downloads of your content hosted on CloudFront with Cognito authentication using cookies and Lambda@Edge

sample-lambda-microvm-claude-managed-agents. Python

dep. A little Node.js dependency installer for module end-users

agentcore-cli. The terminal experience for AgentCore!

aws-blocks. Composable building blocks for full-stack AWS apps — define infrastructure and runtime code together with end-to-end type safety using TypeScript, local mocking, and native client codegen for Kotlin, Swift, and Dart.

shell. Give your agent a shell without giving it the keys to your machine.

omnigent. Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

open-code-review. Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

SkillSpector. Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

coreutils. Coreutils for Windows: Installer & Packaging

headroom. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

sample-openai-on-aws. Production-ready deployment patterns for running OpenAI Codex at enterprise scale on Amazon Bedrock — with corporate SSO, optional quota enforcement, and observability built in.

defending-code-reference-harness. Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

sample-multi-agent-orchestration-chat-on-agentcore. Build & Share AI agents with your team. Full AgentCore, Full Serverless, Full TypeScript Sample

agent-scripts. Scripts for agents, shared between my repositories.

threat-composer. A simple threat modeling tool to help humans to reduce time-to-value when threat modeling

agentcore-book. 書籍「Amazon Bedrock AgentCore実践入門」のサンプルコード

slack-cli. Create, develop, and deploy Slack apps from the command-line ✨

chatkit-js. TypeScript

openai-cli. Official CLI for the OpenAI API

ripgrep. ripgrep recursively searches directories for a regex pattern while respecting your gitignore

warp. Warp is an agentic development environment, born out of the terminal.

perry. A native TypeScript compiler written in Rust. Compiles TypeScript directly to executables using SWC and LLVM.

react-email. 💌 Build and send emails using React

claude-desktop-buddy. Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

electrobun. Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

fastmcp. 🚀 The fast, Pythonic way to build MCP servers and clients.

mux. A desktop app for isolated, parallel agentic development

wterm. A terminal emulator for the web

aimock. Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.

sdk-typescript. A model-driven approach to building AI agents in just a few lines of code.

agent-skills. Production-grade engineering skills for AI coding agents.

kanban. Launch a local web app that runs CLI agents in parallel

meta-harness-tbench2-artifact. Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)

drawio-mcp. JavaScript

hermes-agent. The agent that grows with you

LiteRT-LM. LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

GLM-OCR. GLM-OCR: Accurate × Fast × Comprehensive

aws-iot-connected-product-demo-badge. C

cq. An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.

onecli. Open-source credential gateway with a built-in vault. give your AI agents access to services without exposing keys.

gsd-2. A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

pm-skills. PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

skills. skills for coding agents related to marimo

graphiti. Build Real-Time Knowledge Graphs for AI Agents

three-stars. Accelerated Speed + Step + Small deployment tool for AI Agent on AWS

dev3000. Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.

aix. Build AI apps with the polish of ChatGPT, v0, and Grok. Coming soon.

portless. Replace port numbers with stable, named local URLs. For humans and agents.

agent-plugins. Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.

amplify-backend-vscode. VSCode Extension to explore Amplify Gen2 backend resources

cli. 📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.

slidev. Presentation Slides for Developers

ext-apps. Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

claude-agent-sdk-typescript. Shell

claude-agent-sdk-python. Python

playwright-cli. CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.

bedrock-agentcore-sdk-typescript. TypeScript

openresponses. TypeScript

mcp-remote. TypeScript

skills. Skills Catalog for Codex

mcp-cli. Python

awesome-claude-skills. A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

skills. Public repository for Agent Skills

a2ui. TypeScript

Kiro. Kiro is an agentic IDE that works alongside you from prototype to production.

mcp-aws-handbook. Python

sample-amazon-bedrock-agentcore-fullstack-webapp. Starter template for deploying AI agents with Amazon Bedrock AgentCore. Complete infrastructure scaffolding with authentication, API, and web interface - all automated in one command.

agentcore_hands_on. Amazon Bedrock Agentcore * Terraformのハンズオンリポジトリ

enterprise-deep-research. Salesforce Enterprise Deep Research

remote-mcp-based-on-aws-managed-services. The simple example of remote model context protocol server built with AWS managed services.

vibesdk. An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack

mcp-run-python. MCP server to run Python code in a sandbox.

vespa. The AI search platform

ai-elements. AI Elements is a component library and custom registry built on top of shadcn/ui to help you build AI-native applications faster.

spec-kit. 💫 Toolkit to help you get started with Spec-Driven Development

sample-developer-tutorials. Shell

elysia. Python package and backend for the Elysia platform app.

agents.md. AGENTS.md — a simple, open format for guiding coding agents

openai-agents-python. A lightweight, powerful framework for multi-agent workflows

mastra. Mastra is the modern TypeScript framework for AI-powered applications and agents.

deepagents. The batteries-included agent harness.

liftkit. Components from design to production

streamdown. A drop-in replacement for react-markdown, designed for AI-powered streaming.

tools. A set of tools that gives agents powerful capabilities.

agent-builder. An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

lmstudio-python. LM Studio Python SDK

biome. A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

jan. Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

AIShell. An interactive shell to work with AI-powered assistance providers

langgraph-codeact. Python

Tutel. Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

aws-lambda-deploy. Deploys a Lambda function.

agent-ui. A modern chat interface for AI agents built with Next.js, Tailwind CSS, and TypeScript.

agno. Build, run, and manage your own agent platform.

serena. A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

assistant-ui. Typescript/React Library for AI Chat💬🚀

tsumiki. tsumiki

text-generation-inference. Large Language Model Text Generation Inference

s3vectors-embed-cli. A CLI facilitating semantic similarity search on media in Amazon S3 via AWS Bedrock and Amazon S3 Vectors.

bedrock-agentcore-starter-toolkit. Python CLI toolkit for Amazon Bedrock AgentCore (legacy). For new projects, use the AgentCore CLI: https://github.com/aws/agentcore-cli

bedrock-agentcore-sdk-python. Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with AWS-managed infrastructure.

agentcore-samples. Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

.github.

browserless. Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.

mcp-gateway. docker mcp CLI plugin / MCP Gateway

voltagent. AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

awesome-copilot. Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

power-assert-monorepo. Power Assert in JavaScript - Provides descriptive assertion messages through standard assert interface. No API is the best API.

WaterCrawl. Transform Web Content into LLM-Ready Data

ink. 🌈 React for interactive command-line apps

LLM100knok. CSS

amazon-q-developer-cli-autocomplete. Rust

mcpb. Desktop Extensions: One-click local MCP server installation in desktop apps

oh-my-logo. Display giant ASCII-art logos with colorful gradients in your terminal — like Claude Code or Gemini CLI.

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

mcp-gateway-registry. Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/Entra integration.

mcp-oauth2-aws-cognito. MCP Server Authorization Example with AWS Cognito

genkit. Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

finch. The Finch CLI is an open source client for container development

trykernel. Try Kernel

promptz. Resource Library for AI-assisted software development with kiro

well-architected-iac-analyzer. Sample Generative AI tool for evaluating Infrastructure as Code and architecture diagrams against AWS Well-Architected best practices.

modelcontextprotocol. Specification and documentation for the Model Context Protocol

edit. We all edit.

goose. an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

container-use. Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

microsandbox. 🧱 easy, fast and local-first microVM runtime

aqd-cli-workshop. This is a hands on tutorial that will help you explore and get up to speed with Amazon Q CLI.

harness-sdk. Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

nova-click. Python

suna. The Company AI Command Center

mcp-handler. Easily spin up an MCP Server on Next.js, Nuxt, Svelte, and more

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

registry. A community driven registry service for Model Context Protocol (MCP) servers.

arctic. Java

mcp-on-lambda. TypeScript

amplify-next-template. This is a Next.js starter for building a fullstack app with AWS Amplify.

context7. Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

codex. Lightweight coding agent that runs in your terminal

run-model-context-protocol-servers-with-aws-lambda. Run existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions

vexa. Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

mcp. Open source MCP Servers for AWS

llmstxt. convert `sitemap.xml` to `llms.txt`

amazon-bedrock-agent-samples. Example Jupyter notebooks 📓 and code scripts 💻 for using Amazon Bedrock Agents 🤖 and its functionalities

playwright-mcp. Playwright MCP server

Second-Me. Train your AI self, amplify you, bridge the world

5ire. 5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

Dive. Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨

amazon-q-developer-cli. ✨ Agentic chat experience in your terminal. Build applications using natural language.

bedrock-engineer. Universal AI Agent using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

bedrock-chat. AWS-native chatbot using Bedrock

generative-ai-use-cases. Application implementation with business use cases for safely utilizing generative AI in business operations

anthropic-on-aws. Jupyter Notebook

claude-quickstarts. A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

tavily-mcp. Production ready MCP server with real-time search, extract, map & crawl.

open_deep_research. Python

python-sdk. The official Python SDK for Model Context Protocol servers and clients

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

agent-squad. Flexible and powerful framework for managing multiple AI agents and handling complex conversations

rivet. The open-source visual AI programming environment and TypeScript library

agent-book. Jupyter Notebook

dspy. DSPy: The framework for programming—not prompting—language models

storm. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

langgraph-agents-with-amazon-bedrock. Jupyter Notebook

bedrock-access-gateway. OpenAI-Compatible RESTful APIs for Amazon Bedrock

amazon-bedrock-client-for-mac. A native macOS client that brings Amazon Bedrock's AI models directly to your desktop. Access Claude Opus 4.8, Sonnet 4.6, and other foundation models through a clean interface designed for macOS, with system-wide quick access and full AWS integration.

cdk-iot-core-certificates-v3. AWS CDK construct for managing certificates, policies and things for AWS IoT Core

ogx. Open GenAI Stack

sagemaker-studio-apps-lifecycle-config-examples. Python

agents-for-amazon-bedrock-blueprints. TypeScript

crawlee. Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

langchain-aws. Build LangChain Applications on AWS

deep-learning-containers. One stop shop for running AI/ML on AWS.

stormcrawler. A scalable, mature and versatile web crawler based on Apache Storm

cohere-toolkit. Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

search_with_lepton. Building a quick conversation-based search demo with Lepton AI.

Vane. Vane is an AI-powered answering engine.

phoenix. AI Observability & Evaluation

dify. Production-ready platform for agentic workflow development.

bedrock-book. 書籍「Amazon Bedrock 生成AIアプリ開発入門」のサンプルコード

llama_index. LlamaIndex is the leading document agent and OCR platform

grok-1. Grok open release

amazon-bedrock-serverless-prompt-chaining. Build complex, serverless, and highly scalable generative AI applications with prompt chaining.

chainlit. Build Conversational AI in minutes ⚡️

Authenticator. Authenticator generates 2-Step Verification codes in your browser.

aws-lambda-web-adapter. Run web applications on AWS Lambda

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!