Openai agents

🤖 Enhance your GitHub Copilot experience with curated prompts and instructions for diverse languages and tasks to boost productivity and creativity.

Every model. One interface. — A cross-platform AI desktop client.

⚡ A macOS menu bar app for Codex power users: real-time quota visibility, multi-account relay, and all-device token cost syncing through iCloud. Pure Swift.

Free Claude / Free Claude Code — use Claude Code & Claude Desktop with any AI provider (OpenAI, Gemini, Grok, DeepSeek, OpenRouter, Groq, NVIDIA NIM, GLM, Kimi…). Cross-platform desktop app.

using the OpenAI API from the FFXIV in-game chat

Fast, lightweight search engine for Dart/Flutter with fuzzy search. 4-level priority ranking across name, subtitle, and searchData for fast, relevant results that handle letters, numbers, and emojis 🐙

MCP server for Loxone Miniserver — expose smart-home rooms, controls, and commands to Claude and other AI assistants

AI recipe generator from fridge ingredients — Google Gemini Vision + OpenAI + Streamlit | Generative AI | LLMOps | Python

Welcome to the "UstazGPT" repository! This AI Chat app is designed to provide a platform to ask questions and learn about Islamic beliefs, practices and culture. It uses OpenAI to provide users with an interactive conversation experience.

一款针对 LLM 输入侧审查的精确逆向分析工具。自动定位 NewAPI、OneAPI 及任何实施基于字典规则进行 Prompt 过滤的 API 网关中的敏感关键词 | A precision reverse-engineering tool for LLM input censorship. Automatically pinpoints blocked keywords in NewAPI, OneAPI, and any API gateways enforcing dictionary-based prompt filtering.

Unofficial Home Assistant custom integration using ChatGPT/Codex OAuth for conversation and image analysis.

The action layer for AI agents. Proof of what your agent actually did, not what it claimed.

MCP server for Zooza — natural language class scheduling, attendance tracking, and booking management for dance schools, language academies, swim schools, sports clubs, and activity franchises. Works with Claude and ChatGPT.

QuickForge AI: A production-ready fullstack template combining FastAPI (Python) and TypeScript for rapid AI prototype development. Designed for freelancers and AI entrepreneurs who need to quickly build and deploy professional applications with modern development practices, testing frameworks, and CI/CD pipelines.

Co-creating knowledge with AI

WhisperForge is a Python tool that leverages OpenAI's Whisper model to transcribe large audio files. It automatically splits files into manageable chunks, processes them, and combines the transcriptions into a single document. Ideal for handling lengthy recordings and generating clear, organized transcriptions.

AI Vibe Coder Built with Tanstack Start and OpenAI

A modern macOS browser built with SwiftUI and WebKit, featuring integrated AI support (MLX, Ollama, OpenAI, Mistral) and a beautiful unified interface.

Transform natural language queries into comprehensive Facebook Ads competitive intelligence using N8N automation and AI-powered data extraction.

🤖 AI-powered tool that transforms UI designs into structured development blueprints

Does ChatGPT recommend your store? Live AI brand-visibility audit for Magento 2 — scores how ChatGPT, Claude, Perplexity, Gemini & Groq mention, cite and recommend your brand (0–100, A–F). Admin dashboard, CLI, cron & CI gate. Extends angeo/module-aeo-audit. Free & MIT.

The Agent Reliability Stack: fit, guard, snap, vet, cast. One landing page for all 11 npm + 6 PyPI packages.

Visual AI Workflow Constructor & IDE Assistant. Build autonomous agents, automate browser/desktop tasks, and patch code via drag-and-drop pipelines.

Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust binary.

Local-first AI coding usage dashboard for Codex, Claude Code, and Cursor — tokens, credits, USD estimates, native GUI, and WakaTime sync.

Codex CLI session analyzer - generates HTML usage reports with AI-powered suggestions

Site IQ - domain-in AI website-intelligence report (SEO/Tracking/AI-Readiness/Tech) powered by an n8n + Firecrawl pipeline. Next.js 16 + Supabase.

Secure, role-based medical records platform with encrypted vaults, consent governance, emergency access, and GPT-4o AI summaries.

Summarize YouTube comments 💬 filtered by a prefix, using ChatGPT, and save to JSON 📁. Fun project! 😄

Free OpenAI-compatible API that forwards requests to GPT via browser extension - for testing

Optimize websites for AI search engines with a universal TypeScript engine supporting Next.js, NestJS, WordPress, and Shopify integration.

Integrate AIProxy with Expo apps

AgentOx - Agentic Tool Security Platform (MCP + A2A + OpenAI tool_use)

A Habbo client AI agent for interacting with other users naturally

AI-driven Polymarket trading bot designed to analyze prediction market data and execute semi-automated trades using OpenAI and Claude models. The system evaluates market sentiment, probabilities, and trading signals to assist with intelligent decision making in prediction markets.

See what your AI coding cost and produced, from the logs already on your disk. Offline, no account.

AI-powered platform for capturing, enhancing, and organizing ideas using voice input and community collaboration.

Pack your codebase into a single file for AI analysis

AI-powered mock interview platform designed to help students prepare for placements through personalized AI interviews, adaptive questioning, real-time voice interaction, and instant performance analytics.

AI-Powered Burp Suite extension for elite bug bounty hunting. Detects HIGH/CRITICAL vulnerabilities using LLMs.

AI SEO for WordPress — get cited by ChatGPT, Perplexity, Claude, Gemini & Google AI Overviews. llms.txt generator + Markdown endpoints + FAQ schema + 31 AI crawler controls + E-E-A-T + WebMCP. Works alongside Yoast, Rank Math, AIOSEO. Zero frontend bloat. By POSIMYTH.

🎤 Control your world with Jarvis, a voice-activated AI assistant that simplifies tasks and enhances productivity.

⚡ Schema-preserving JSON translation for i18n with JSONPath, key mapping & 17+ LLM providers · 保持 schema 的 JSON 翻译工具，支持 JSONPath、键映射与 17+ LLM，专为 i18n 设计

Bash scripts for an agent-driven development and review loop with human sign-off at the end.

GitHub Action + CLI that auto-writes PR descriptions, adds labels, and reviews code using OpenAI

The fastest measured, optimized local Codex usage meter for tokens, sessions, and estimated OpenAI cost.

OpenAI API powered Twitch chat bot that allows users to ask questions and receive answers via TTS.

🌤️ A sleek weather app leveraging OpenWeather API and OpenAI's ChatGPT 🤖 for real-time weather updates and personalized suggestions on activities, attire, food, places to visit etc. based on weather data and location. Built with React ⚛️, TypeScript, TanStack Query, Tailwind and Redux for a responsive, user-friendly experience. 🌍💡

PDFInsights is an AI-powered chat application that allows users to interact with PDF documents. This application enables users to ask questions and get insights from PDF documents using natural language, making it a valuable tool for students, researchers, and professionals

Async web crawler powered by Playwright headless Chromium — JavaScript rendering, AI-powered extraction (OpenAI / Anthropic / Google), CSS rule engine with visual preview, and a full PySide6 desktop GUI. SQLite WAL crash recovery, proxy circuit breaker, RFC 9309 robots.txt, ReDoS-immune regex, 3,822 tests. pip install astrocrawl[full,gui,fast].

Rust-native, local-first, auditable structured extraction with schemas, benchmarks, persistence, and operational reliability

🤖 CLI to fine-tune GPT-3.5 Turbo models rapidly. 💬

Codex Computer Use Fix: repair Computer Use and bundled local plugins on Windows after updates or restarts.

An open source AI based application that allows you to literally draw and build mobile applications. (Requires GPT-4 Access Key)

Run your own LLM inside Warp — local adapter for any OpenAI-compatible provider

An AI-powered node.js chatbot for Telegram integrated with OpenAI Streams and ToolChoices 🤖💜

OLD - AI-powered color system generator SAAS app. Creates accessible color palettes for design systems with a Nextjs based REST API and webhooks.

Zero-dependency, spec-compliant streaming toolkit for LLM responses in Rust (SSE, incremental JSON, OpenAI/Anthropic delta accumulators).

Whisperer is a privacy-first, browser-based AI chat application that stores all data locally using the pglite library. It supports advanced AI interactions with Retrieval-Augmented Generation (RAG) using pgvector for enhanced, context-aware conversations, including seamless interactions with PDF documents.

angel is an autonomous AI agent with multi-channel support and persistent memory.

飞鹊 (Feique) — 团队 AI 协作中枢 | Team AI Collaboration Hub. 从个人提效到团队协作，让 AI 融入工作的每个环节。

Open-source AI Gateway, all enterprise features included.

AI Telegram personal finance bot with cashflow forecasting and overdraft prediction

Codex-style apply_patch tool extension for pi

Local-first API router for MiniMax + Kiro (AWS CodeWhisperer / Amazon Q) upstreams — OpenAI & Anthropic compatible, multi-account fallback, switchable Kiro IDE/CLI persona, RTK + Caveman compression, built-in dashboard (Hono + SQLite + Preact)

Claude Code profile manager and local compatibility proxies. Easily switch profiles and run Claude Code using Gemini, Groq, Mistral, NVIDIA NIM, Hugging Face, OpenRouter, and OpenAI-compatible APIs.

OpenAI-compatible proxy for Claude Pro/Max - use with Cline, Roo Code, Kilo Code

A terminal-native, zero-infrastructure local RAG pipeline and developer intelligence hub powered by OpenAI Codex, ChromaDB, and Groq/Gemini.

Multi-user Streamlit RAG app with SQLite auth, Qdrant vector search, document upload, per-user collections, chat with citations, and configurable OpenAI or Ollama models via Docker/local development.

一个会读写代码、操控终端与网页的桌面 AI 智能体（Electron + Python）。A desktop AI agent that reads your code, runs your terminal, and drives the web.

Build and deploy large language models with Open Qwen, a PyTorch-based framework for efficient, flexible AI development and research.

🔥 A local-first AI agent mainframe built in Rust with capability-based security and event-stream architecture... 💎 Preloaded with a trusty assistant Leon the chameleon, a fully customizable to user needs featuring quantum encrypted internal blockchain security... 🦎

Agentic coding CLI for a-Shell

Control Claude Code / Codex on your home PC from your phone via QQ — text a task, the agent codes in your real project, results return to chat. Windows · pure Python stdlib · zero pip deps · self-healing watchdog.

Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.

Codex Orchestrator for Codex App: Loop Engineering with worktree sessions, heartbeat monitoring, persistent ledger, review routines, and evidence-label gates.

An AI deliberation instrument with visible protocol: eleven philosophers as concurrent seats, virtue-scored opinions, a synthesis, and a first-class minority report. Not prompt choreography. Methodology, not metaphysics.

Framework-agnostic Go package for integrating AI-powered chat functionality into any web application. It features out-of-the-box support for popular Go web frameworks, a flexible model abstraction for using OpenAI, Anthropic, xAI, Google Gemini, Meta, and more.

Run Claude Code-style AI coding in the terminal with free Groq, OpenAI, or Gemini API support

A **standalone** Discord bot with LLM, VOICEVOX, and KaTeX support.

Turn any YouTube video into agent-ready research markdown: transcript -> structured LLM breakdown -> optional deep technical dive.

Xcode Intelligence 使用 deepseek

Runnable LangGraph workflow examples covering conditional routing, parallel execution, iterative refinement, approvals, and checkpoint recovery.

Detect whether a cheap third-party Claude/GPT API key is actually a man-in-the-middle proxy that intercepts and degrades your traffic. Claude Code skill + check scripts + reporting guide.

TaskFlow AI is an intelligent daily planner that transforms natural language descriptions into structured, prioritized daily plans. Built with Flask and OpenAI GPT, it automatically categorizes tasks, estimates time, and generates optimal schedules. Features include voice input, dark mode, and responsive design.

Describe images in the WordPress Media Library using a local large language model. Generates titles, captions, descriptions, and alt tags.

AI memory layer for .NET - runs in Blazor WASM, no backend required

Power Claude Code, Codex CLI, and more with your Copilot subscription.

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

反封号.skill — Claude Code / Anthropic / OpenAI account suspension risk detection, IP cleanliness scoring, compliance preflight, and appeal-packet skill. Compliance-only; no ban evasion.

Your private AI assistant. BYOK chat (OpenAI, Anthropic, OpenRouter) and schedulable automations connected to Gmail, Drive, Calendar, and Discord. Self-hosted.

Transparent HTTP proxy that redacts secrets and PII before they reach LLM providers. Works with OpenAI, Anthropic, Gemini, and 25+ providers.

Free, self-hosted AI coding assistant for VS Code — local Ollama models, Anthropic Claude, or any OpenAI-compatible server. Full agent loop with tool use, inline completions, and MCP support.

AI-powered project handover for Claude Code and Codex: onboarding docs plus privacy-filtered AI memories, verified against current code before import.

🌐 Visualize Claude Code agents, skills, and commands with this interactive tool for easy navigation and understanding of complex relationships.

Runtime token proxy + intelligence dashboard for LLM tools. Intercepts API calls, strips waste, tracks costs — for individual developers and Fortune 500 teams.

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.

Beautiful, fast, fully native Android chat client for OpenAI, Anthropic, Groq, OpenRouter & any OpenAI-compatible endpoint. Streaming, encrypted on-device API keys, 100% Jetpack Compose + Material 3.

RAG over 289 of Edward Witten's papers (1976–2026): his arXiv corpus + 44 pre-arXiv recoveries. BGE-large + FAISS + pluggable LLM backend (default Claude, also OpenAI/Ollama) with strict citation grounding.

Native agent-graph runtime written in C++20