Code agents

Stream Recording for TikTok, Twitch, Kick, YouTube, AfreecaTV, and Pandalive. Just add your live streams, and they'll be automatically captured and saved for you to watch anytime.

A GPT-powered SQL assistant that understands human language and talks to your database. Surprisingly useful. Seriously.

Generate audio transcripts and summaries by using OpenAI.

A customizable GPT-3.5/4 chat application built with Flask and plain HTML, CSS, and JavaScript

This code example is a FastAPI server that contains multiple API endpoints for interacting with an OpenAI model.

Comparing vector-only RAG with GraphRAG (neo4j+milvus) for semantic and structural code search in JavaScript.

🐙 AI coding assistant for the terminal. Open-source CLI tool that guides coding with a chat-style agent, helping developers write and debug code faster today.

Python Streamlit web app utilizing LangChain and the OpenAI API GPT 3.5 Turbo language model to generate example movie concepts based on the AI director(Spike Lee, Quentin Tarrentino, Wes Anderson) and user input, and then the DALLE2 image generation model to generate relevent movie poster.

Practical use of Azure API Management's AI Gateway to manage Azure OpenAI operations.

Companion code for the "Building AI-Powered Apps with RubyLLM" workshop

This project is an advanced WhatsApp bot that leverages artificial intelligence for automated audio transcription, document summarization, and scheduling of future messages. It uses Whisper for transcription and offers a choice between OpenAI's API and the Ollama local model for document summarization.

Uncover hidden connections and find the most semantically similar text to your search term with just a CSV file, OpenAI's text embedding model, and AWS Lambda.

Yet another OpenAI Translator for vscode. Fork from:https://github.com/yetone/openai-translator

This portfolio serves as a showcase of my projects, skills, and experience as a web developer. It's designed to provide an overview of my capabilities and to help others learn more about me and my work.

Speech to Text Transcription using OpenAI Whisper v3 and FastAPI

LLM tools

build a chatbot for Retrieval Augmented Generation using SurrealDB and OpenAI's API.

Use the OpenAI TTS (text-to-speech) model to read any selected text on your Mac with a keyboard shortcut. Bring your own OpenAI API key.

Create embeddings for your Eloquent models to use with OpenAI

A static-page vanilla-js interface for various LLM APIs (OpenAI, Claude, Gemini, Together).

Building RAG With OpenAI GPT-4o(omni) Model Using Objectbox Vector Database

My AI is a web application that allows you to generate images, videos, music, text and code using OpenAI's GPT-3 API. It is built with Next.js and Tailwind CSS.

Useful speech to text tools that use Whisper under the hood (API/local)

This configuration is from the ChatGPT source code.

Make OpenAI batch easy to use.

PaperCheckAI is a cutting-edge, open-source platform-as-a-service leveraging state-of-the-art multimodal large language models (LLMs) to autonomously digitise, interpret, and evaluate handwritten long-form answer sheets in compliance with custom rubrics, ensuring scalable, secure, and explainable AI-driven assessments for educational institutions.

macOS menu bar app + desktop widget showing Claude usage in real time — session, weekly, Sonnet 4.5 & extra credits. One-command install, no Apple Developer account needed.

A beautiful Claude Code management UI / built with Claude Code 🤖

⭐ Integrates Claude Desktop with Google and Atlassian workspaces

🔧 Turn any CLI or MCP server into an Agent Skill — zero process overhead, 98% fewer tokens. Kill MCP zombie processes. Works with Claude Code, Codex, Gemini CLI & 26+ platforms.

Control Claude Code from your phone — E2E encrypted, self-hosted, open source

Anthropic's Computer use implementation in Nodejs

Global Notion workspace-accessible MCP server for all Notion pages within the workspace

Idiomatic Kotlin wrapper around com.anthropic:anthropic-java — suspend / Flow / sealed types over the official Anthropic Java SDK.

An Android App recreating the Simon Says game. Uses MediaPipe to run an LLM on device using RAG

Rapid Document Ranking, Powered by Lightweight Models.

Open Multi-Modal Personal Assistant

💵 Real-time financial intelligence for your codebase. Implemented via VS Code extension + Web Sandbox (Next.js, LangChain, Gemini, MongoDB)

A Chrome extension that uses PromptAPI and vector embeddings to help users quickly find answers about the current website's content.

local-first pipeline that turns notes into a research-style draft: extract keywords → fetch arXiv → rank (SPECTER) → summarize (PEGASUS). No chat, no API keys.

Turkish Constitution RAG assistant using Python, FastAPI, local AI, semantic retrieval, and structured legal data for legaltech experiments.

The MCP-RAG project is an AI agent framework based on the Multi-Context Protocol that connects various data sources (MySQL, documents, RAG search) with LLMs. It supports HTTP API, SSE chat, an MCP router, batch workers, and a React + Tailwind frontend.

WovenSnips: A Lightweight, Free, and Open-source Implementation of Retrieval-Augmented Generation (RAG) using Straico API

Scrappe-Tout is a web scraping tool designed to convert HTML documentation into clean, organized Markdown files. It automatically handles navigation menus, removes duplicate content, and generates descriptive filenames for easy reference.

Welcome 👋 to the WetroCloud SDK. An easy-to-use toolkit for integrating with the WetroCloud API. Manage collections, work with resources, and run AI-powered queries including Retrieval-Augmented Generation (RAG)

AI cup contest

Structure-aware text chunking library for code, prose, and markup files. Intelligently splits files into context-rich chunks while preserving semantic boundaries. Supports 15+ programming languages, deterministic output, and zero external dependencies. Perfect for RAG systems, code analysis, and LLM context optimization.

腾飞智能助手是基于钉钉平台的AI助手，集成了大型语言模型、知识库、对话记忆储存和多种工具能力，提供智能问答、任务处理和信息检索服务。深度集成钉钉构建智能待办/日程/日志/审批系统等，实现自然语言到API的自动转换，用户操作步骤减少70%。

A memory store for LLM agents. Hybrid BM25 + dense retrieval, cross-encoder reranking, clustered retrieval-induced forgetting (RIF), and an optional LLM enrichment layer at write time.

RagE (RAG Engine) - A tool supporting the construction and training of components of the Retrieval-Augmented-Generation (RAG) model. It also facilitates the rapid development of Q&A systems and chatbots following the RAG model.

Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.

RAG/StructRAG using SQLite, C# and Ollama

Code for the USDA Branded Food Dataset pipeline and the USDA Food Assistant. This project consolidates USDA FoodData Central data into a structured dataset, along with an interactive tool that allows for conversational exploration of food items, nutrients, and ingredients.

Typescript client for Unbody's API

RAG-Enhanced Fake News Predictor analyzes news content using multi-API verification, AI assessment, and machine learning models. It cross-checks articles against a knowledge base, validates news authenticity, and provides detailed insights, helping users identify fake or misleading information efficiently.

TinyRAG is a minimalist Python library that enables developers to rapidly build RAG-powered applications. It supports a flexible range of LLM endpoints and provides a clean API for combining retrieval with generation.

🧠 Claude Code plugin marketplace featuring Second Brain - an agentic workflow system with persistent memory and tribal knowledge. Transform Claude from goldfish to elephant with cross-session learning.

Test, compare, and optimize your AI prompts in minutes

This repository provides a template for building Large Language Model (LLM) powered microservices using FastAPI. It's designed to help you quickly set up and deploy AI-driven APIs that leverage the power of LLMs like GPT-3, GPT-4, Claude or other similar models.

Automated pipeline for real-time market analysis: Scrape live job data, generate structured CSVs, and create analytics scripts using Kiro with Bright Data MCP.

EDAgent is a skill-based LLM agent designed to assist EDA research workflows, routing user requests to appropriate skills for code analysis, debugging, experiment setup, and research automation.

AI agent skill that creates formal, verifiable proofs of claims — every fact computed or cited, never asserted

Knowledge completion layer for Claude Code - finish your thoughts and make them reusable across sessions and agents

Merge gates and safety checks for AI coding agents. Works with Claude Code, Cursor, Windsurf, Codex via MCP. Detect scope violations, missing tests, and risks before merge.

MyCodex desktop AI agent workspace for Codex + Hermes workflows, WeChat control, browser automation, file artifacts, and token-light setup.

A multi-provider desktop agent IDE for tool-using local and cloud models.

Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.

Persistent memory for AI coding agents. Never solve the same bug twice. Works with Claude Code, Gemini CLI, Codex CLI, Kimi CLI.

A multi-server Discord control plane that exposes Discord operations as MCP tools, resources, and prompts for AI clients, with a built-in conversational AI agent.

🐕 AI-Powered Risk Assessment for Claude Code — 7-layer pipeline, native notifications, menu bar dashboard. One line install.

Paste Mac clipboard text and screenshots into remote iTerm SSH sessions.

AI agent skill: tell Claude Code, Codex, Gemini or OpenClaw to upload your recording to YouTube — it downloads from Drive, transcribes, generates timestamps and metadata automatically.

Autonomous AI Agent SDK for React Native & Expo — AI reads your live UI, acts via natural language, real-time voice agent (Gemini Live), and AI-powered testing via MCP (Model Context Protocol). One component. Zero config.

Next.js 16+ caching architecture. Applies to any App Router project regardless of domain.

Claude Code plugin that automates the entire React Native app lifecycle — from market research to App Store & Google Play submission. Harness engineering with Generator-Evaluator separation, file-based handoff, and contract negotiation.

Give one OpenClaw session durable memory, topic-aware continuity, and bounded token growth.

An oncall AI agent to debug production issues and minimize loss

AI command center for the servers you already SSH into — diagnose, fix, and verify over SSH. macOS, Linux, Windows (preview), iPhone, Android.

14 Claude Code skills for content creation, knowledge management, and media automation

MCP Kill-switch for AI agents. Validates infrastructure operations before execution. Fail-closed. Evidence-backed.

基于 LangGraph + MCP + FastAPI(SSE) + Streamlit 的本地知识库问答助手

a tool that reduces token usage and request waste in coding-agent workflows by selecting, compressing, caching, and budgeting repository context

Ready-to-use AI agent templates with complete workflows that make Claude smarter at specific development tasks.

15 Shinchan character agents that debate, plan, execute, and learn. Stop doing everything yourself - orchestrate a team.

The Missing sudo Command for AI Agents.

An agentic AI Chrome extension that autonomously understands website APIs, analyzes page structure, and generates custom scripts through natural language prompts. Think of it as a Cursor-like AI assistant, but for any website you're browsing.

Awesome list of AI agents (2026 Edition) — Curating 300+ frontier frameworks, coding agents, MCP protocols, computer use, and commerce rails — featuring LangChain, CrewAI, AutoGPT, Claude Code, Cursor, Devin, and more.

Cordon provides the guardrails for corporate teams adopting code generation tools.

Security-first Rust CLI for dependency risk scanning, API workflow testing, and shared coding memory.

KNDL — Knowledge Node Data Link. Anthropic just shipped Memory for agents — a filesystem. But filesystems are dumb about confidence, time, and source. Agents fill them with markdown that can't be queried, won't decay, and loses provenance the moment it's written.

Open-source operating system for running an AI agent company on your own machine. Clone, run, and a localhost wizard walks you through defining your company — KPIs, org structure, agent templates, connectors. Bring your own Claude Max.

One markdown file that tells an AI agent how to do your cold outreach. Open spec + Claude Code skill.

Curated Knowledge API for AI Agents — 68 MCP tools, 200+ skill packs, 46K chunks, semantic search over 670K vectors, 5-layer validation pipeline. Works with Claude Code, Cursor, Cline, Windsurf.

A structured Node.js starter for AI-native development—designed for alignment, clarity, and scalable systems.

crosswire (xw) — Cross-machine communication protocol for AI coding agents. File-based, SSH-bridged, agent-agnostic. Zero dependencies beyond Bash.

A curated list of Agent Skills for navigating life in Israel

AgentLog is a lightweight event bus for AI agents built on append-only JSONL logs. Agents publish and subscribe to events via HTTP/SSE, enabling simple, replayable, and debuggable multi-agent workflows.

Sandbox npm, pip, and AI coding agents in ephemeral macOS micro-VMs

Open-source local dashboard for managing your Claude Code skills and MCP servers, with silhouette-scored clustering to surface overlapping skills.