Openai agents

A centralized registry for discovering and managing LLM model capabilities. Track model features, costs, and limitations across providers like OpenAI, Anthropic and other open source models. Supports both verified model definitions and user-managed entries with local storage.

A flexible and extensible reinforcement learning library for Python, designed for both beginners and researchers.

I am using Nuxt 3 framework with OpenAI's API

LintGPT scans your code for bugs using AI.

Intelligent Applications with Spring AI. Practical integration of LLMs, chat interaction, image generation, and audio transcription in enterprise applications using Spring AI.

OpenAI ChatGPT Laravel package. Laragpt is the perfect package for developers wanting to access the powerful Artificial Intelligence capabilities of OpenAI through an easy to use Laravel interface.

A zig OpenAI API client library

OpenAi.JsonSchema is a lightweight library for generating valid JSON Schema for OpenAI models' Structured Outputs feature. It supports a wide range of types, ensures compatibility with OpenAI's JSON Schema format, and leverages C# descriptions and attributes for schema generation.

BubblesAgent: Open-source AI agent using LLMs (GPT, Gemini, Claude) for automated, large-scale code refactoring and transformation.

OpenAI 兼容的 API 中转代理平台，支持上游账号池负载均衡、用户管理、额度控制、套餐与兑换码系统

ChatGPT Telegram bot

将Aliyun百炼大模型平台的App接口转成OpenAI API接口

A GPT TUI client with proxy supported.

A web-based tool that utilizes GPT-4's vision capabilities to analyze and describe system architecture diagrams, providing instant insights and detailed breakdowns in an interactive chat interface.

🎒 OpenAI驱动的飞书多维表格助手

Automatize local data analysis with team of tool-using GPT agents

Freeswitch Speech-To-Text module

⚡️🤖 A collection of Firebase Extensions built by shiftEscape

Stitch together text-to-speech over 4096 characters via the OpenAI API

Collection of awesome ChatGPT prompts to get better results. Use these with any AI writer to converse smartly.

Webpage to structured data in Rust & LLM

Converting textual descriptions of processes into simplified BPMN diagrams

OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API Client for Crystal

HTTP proxy for accessing Vertex AI with the REST API interface of ollama or OpenAI. Optionally forwarding requests for other models to ollama. Written in Go.

Generate an alt-text description for an image using ollama and llama3.2-vision

[This repo has been deprecated, the latest version of ForexGPT is closed-sourced] ForexGPT presents Forex Rates: Advanced Natural Language Processing for Currency Markets. Gain insights, sentiment evaluation, and text completion using the power of language models.

The Chat-Agent system is designed to execute GPT queries using intelligent tool selection. It leverages a hierarchical approach, dynamically choosing between summarization and Retrieval-Augmented Generation (RAG) tools, further refined to specific implementations within each category.

Monitor and visualize your Claude Code API interactions with Claude Code Proxy. Easily set up a transparent proxy and live dashboard. 🛠️🚀

The DALL-E 3 Voice-Controlled AI E-Ink Art Frame

Whisper in TensorRT-LLM

aido (A.I. do) command

This is a python bot script that reads a pdf file, then it opens a navigator window (Google or Firefox) at chatgpt openai website. and he asked chatgpt to make outlines of the given pdf by chapters (chunks) (note: it does not need to use API Key).

AI screening tools in R for systematic reviewing

This project aims to perform sentiment analysis on tweets related to ChatGPT, a popular language model developed by OpenAI. The dataset used for training and testing consists of 219,293 tweets collected over a month. Each tweet is classified as positive ("good"), negative ("bad"), or ("neutral").

An AI powered n8n workflow generator

An Airtable extension that enables semantic search and Q&A using gpt-3.5

基于 NoneBot 的机器人 / 链接到 ChatGPT + Bing + Stable-Diffusion / q群与qq频道支持

An AI Discord Bot generating text and images, advanced features, full memory, large model choice

Generate summaries of Udemy video transcripts using the OpenAI API

A ready-to-use ASP.NET Core chat application backed by a Minimal API that can be used to test ChatGPT workflows

This MCP server is responsible for generating images for both OpenAI and the Gemini Model.

Filament OpenAI Assistant is a filament plugin that adds a chat page with an Open AI assistant

Multi-agent chat powered by openai-agents-sdk and Streamlit

A simple Python based implementation of a Raspberry Pi based, OpenAI ChatGPT enabled voice assistant

A local reverse proxy that records every LLM request/response to SQLite. No cloud, no data leaving your machine.

This is speech to speech(voice chat) applications. Between of user and AI

A sample demo for building and testing react components and includes a set of unique features including AI component generation and automatic conversion to Azure APIM Widgets

BipedalWalker - AI teaching itself to walk

一款强大的 X (Twitter) Chrome 扩展，支持智能评论生成、批量回复、潜力指数筛选、快速书签管理等功能，提升社交媒体互动效率

AI-powered real estate GPT that provides property insights, market analysis, pricing guidance, and smart recommendations to help buyers, sellers, and investors make informed decisions quickly and efficiently.

Simple bot WhatsApp OpenAI by Irfan Hariyanto

An external retriever for GPTs implemented with Zilliz Cloud Pipelines, a more flexible and economic alternative to default GPTs knowledge base.

Production-ready multi-agent AI system: 8 specialized agents with self-healing, crash recovery, and Board-First coordination. Built on OpenClaw. Supports Anthropic, OpenAI, Google, DeepSeek, Ollama.

Zero-Infrastructure Lip-Synced 3D avatar components for AI voice agents. This library is built with React Three Fiber and AI providers

A comprehensive toolkit for detecting potential hallucinations in LLM responses. Compatible with any LLM API (OpenAI, Anthropic, local models, etc.)

Drop-in RAG and AI agent toolkit for Laravel — parse, chunk, embed, search, chat.

SDK to build Agents in rust. Build and manage complex, self-correcting agent teams. Launch multi-agent systems via configuration files or using an Agent Factory. It's the robust framework for orchestrating intelligent agents using open standards (MCP, A2A).

🤖 Automate WhatsApp interactions with Sofia, your intelligent virtual assistant for lead qualification, meeting scheduling, and AI-driven conversations.

🎨 Create visual AI workflows with Tapnow Studio, a browser-based tool that combines powerful AI capabilities in a single, interactive node editor.

Unified LLM API and agent runtime for Clojure, ClojureScript (and soon Clojure Dart)

MCP server for Google Ad Manager. Manage ad campaigns, orders, line items, and creatives through AI assistants like Claude, ChatGPT, Gemini, Cursor, and VS Code. Automate your ad operations with natural language instead of clicking through the GAM UI. Built by Matious.

The Definitive Guide to Transforming Your AI-Based Software Development with Cursor and Claude Code

Yet Another Agent SDK, CLI, Claw, Agent Platform

Use Claude Code, Gemini CLI, and Codex CLI on remote servers via SSH reverse tunnel

Unified AI API library for ESP32/Arduino - OpenAI, Anthropic Claude, Google Gemini, Ollama with streaming, tool calling, async and conversation memory

Agentic Spec-Driven Development — 13 agents, 58 MCP tools, 10-phase enforced pipeline. From meeting transcript to PR in one command. Install via npm install -g specky-sdd@latest

A comprehensive reference for building and organizing AI agent skills across Claude Code, KiloCode, OpenClaw, and OpenAI Codex. Covers SKILL.md specifications, folder structures, mode-scoped skills, agent orchestration, and self-hosted model configuration.

Open Agent Spec is a declarative YAML standard and CLI for defining and generating AI agents. One spec, any LLM engine (OpenAI, Anthropic, Grok, Cortex, local, custom).

How to stop AI agents from hallucinating and wasting tokens. Working demos: Graph-RAG, semantic tool selection, neurosymbolic guardrails, DebounceHook — built with Strands Agents

MindTrial: Evaluate and compare AI language models (LLMs) on text-based tasks with optional file/image attachments and tool use. Supports multiple providers (OpenAI, Google, Anthropic, DeepSeek, Mistral AI, xAI, Alibaba, Moonshot AI, OpenRouter), custom tasks in YAML, and HTML/CSV/JSON reports.

Run parallel OpenAI Codex CLI agents in tmux with automatic permission approval. Auto-approves command execution, file edit, network access, and MCP tool prompts while preserving sandbox protection. One-liner install for macOS, Linux, and WSL.

Cloud-agnostic Agentic AI & Multi-Modal RAG platform with GraphRAG, intelligent routing, MCP enterprise integrations (Odoo, PostgreSQL), and pluggable LLM providers.

LazyChat — an AI assistant docked inside your ERPNext desk. Chat with your data, draft reports, stage edits (Apply-gated). Bring your own LLM: any OpenAI-compatible or Anthropic key, stays in your browser. Also ships an MCP server (101 permission-scoped tools).

You pick the model per task, with review, evidence, and a PR at the end.

Local-first Codex quota tracker and multi-account switcher for macOS and Windows

♟️ AI-powered chess trainer with Stockfish 18 + LLM coaching. Learn chess with real-time explanations, engine analysis, puzzles, openings, and endgame training — directly in your browser

Search the web in Pi through your Codex subscription.

Hosomaki, the intelligence layer for Linux

Minimal Go agent framework for LLM tool-calling loops (v1.0, stable). Typed tools, parallel execution, three hooks, streaming progress, snapshot resume, prompt caching across iterations. Anthropic Claude, OpenAI GPT-5, Google Gemini via pi-llm-go.

Open-source, fully automated multi-agent content pipeline: Web content → AI Script → Voiceover → Video → Telegram Approval → Social Media Upload

One interface for your whole data stack, with built-in safeguards and a simpler workflow for your team. Written in Rust. Docker not needed.

Deterministic multi-provider AI-agent orchestrator — ODA loops, GPT/Claude/Gemini/Kimi adapters, safety controls, event log

EduBridge is a full-stack web application designed to provide interactive learning resources, quizzes, and AI-driven guidance for students. Built with a Python/Flask backend and dynamic HTML/CSS/JS frontend, it features user authentication, personalized profiles, and easy access to career and skill development content.

Provider-agnostic AI dev pipeline: clarify → plan → build → review → PR across your repos, mixing LLM providers per stage with your own keys. No vendor lock-in, no markup.

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model judgment, not holistic LLM-judge guesswork), with confidence intervals.

A lightweight proxy that converts Anuneko services into a standard OpenAI API format. 将 Anuneko 服务转换为标准 OpenAI API 格式的代理服务。

A Python trading bot connecting directly to Interactive Brokers (IBKR) via ib_insync for live market data and automated order execution, with optional OpenAI integration for advanced signals.

专门面向中文的提示词工程指南

🚀 Typollama – AI Writing Assistant – A Chrome extension for real-time text enhancement using local and cloud AI models. Instantly spellcheck, proofread, and customize AI-powered writing with keyboard shortcuts and right-click integration. ✨

Talk to your Mac — a native macOS voice assistant that sees your screen, drives your Mac, and answers back. Powered by the OpenAI Realtime API. Open source.

OpenAI Security Console - Python3 AI-powered Cybersecurity Framework

AI-powered e-commerce chatbot built with Next.js and MongoDB.

Half game, half experiment. World built out of GitHub issues — describe an idea, AI agents ship it live.

Local AI workbench: plan, queue, route, validate, and hand off long-running work using your already-installed Codex and Claude Code CLIs as hidden workers.

AI-powered MP3 metadata updater to automatically update song details (title, artist, album, year) using OpenAI API or local LLMs via Ollama.

A Bukkit plugin that gives villagers AI capabilities

A minimal browser-agent harness - six tools, any model. pi for the browser.