Openai agents

AI Model Pricing Aggregator - Compare AI model pricing across AWS Bedrock, Azure OpenAI, OpenAI, Google Gemini, OpenRouter, xAI and more

🛠️ Build AI prompts easily with a clean tool featuring live previews, local libraries, and optional optimization for structured design.

NordRelay is a secure remote control bridge for coding agents, connecting Codex, Pi, Hermes, OpenClaw and Claude Code to Telegram, Discord, Slack, WebUI with streaming replies, sessions, files, voice, queues, artifacts and access controls.

Test, red-team, and deploy LLM applications with confidence. Multi-provider support (OpenAI, Anthropic, Gemini), MCP integration, self-play testing, and production SDK.

Privacy-first AI middleware with local PII detection, approval gate, and automatic de-anonymization. Query your documents with any LLM — GDPR, KVKK, HIPAA ready.

Better, open-source, LLM wrapper (user management, text processing, file processing, image generation, web search, local models)

LLM-assistant that searches PubMed, retrieves abstracts or full-texts, and generates answers using OpenAI ChatGPT. Features a custom RAG pipeline, semantic search, and knowledge graph generation.

Streaming-first multi-provider LLM client in TypeScript with home-made tool calling

Asynchronous, massively collaborative coordination layer for agents.

Token-level cost intelligence for AI coding tools — budget alerts, anomaly detection, and multi-tool tracking across Claude Code, Codex CLI, Cline, and Gemini CLI

🐙 Multi-armed mocks for LLM apps - Drop-in replacement for OpenAI/Anthropic APIs for deterministic testing

Lightweight RAG server for the Model Context Protocol: ingest source code, docs, build a vector index, and expose search/citations to LLMs via MCP tools.

A local-first desktop app that finds, reduces, and verifies AI-agent token waste without sacrificing task quality.

Reuse your AI subscriptions. One module, every provider. OAuth PKCE for ChatGPT Plus/Pro, API keys for Claude/Gemini/DeepSeek, device code for Copilot. ~500 LOC, only depends on httpx.

An unofficial fork of OpenAI Codex with multi-account ChatGPT and one-command local models via LM Studio. Save every plan, hop between them mid-task, fall back to a model on your own machine when you want to.

AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any web/Electron app. Automated QA, viewport testing, visual feedback loops.

Local orchestration and routing for AI agents — gateway-first, agent-first, integration-first

agentmemory: persistent memory for coding agents (Claude Code, OpenAI Codex, Cursor, Agent) with local markdown storage, daily logs, scratchpad, and qmd semantic search.

Self-hostable digital restaurant menu — Next.js + Cloudflare Workers + D1, with an optional OpenAI-powered chat assistant. One menu, one deploy. PolyForm Noncommercial.

Home Assistant add-on that replaces Xiaozhi cloud for StackChan ESP32-S3 robot — switchable OpenAI Realtime / Google Gemini Live voice assistant with HA device control. No Xiaozhi account needed.

Self-hosted Prometheus exporter for LLM usage, token, request, and USD cost telemetry across OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, and AWS Bedrock.

Automating short form content creation with AI

MCP server exposing OpenAI's gpt-image-2 for image generation and iterative editing

Code once, run everywhere across Ollama, LM Studio, MLX, HuggingFace, vLLM, OpenAI, Anthropic, and more with consistent APIs for tools, structured output, streaming, media, prompt caching, and secure OpenAI-compatible gateway deployment.

Search, inspect, and export Claude Code, Cursor & OpenAI Codex conversation history

VS Code extension for chatting with local AI models using LM Studio or Ollama.

An open-source BI platform with AI-powered dashboards, real-time chat, and multi-database connectivity. FastAPI + Nuxt 4 + LangGraph.

GNOME Shell extension that tracks Claude and Codex AI usage limits in the top panel

Official MCP server for OrcaRouter — the LLM gateway with auto-routing and fallback chains. Browse models and chat from Claude Desktop, Cursor, Windsurf, or any MCP client.

Markdown-first multi-model AI orchestration in one tmux session. A single coordinator (Chrono) routes scoped markdown task packets across 4 frontier model lanes (GPT-5.6 Sol / Claude Opus 5 + Fable 5 / Gemini 3.5 / Kimi K3) and 73 role-based specialists — with cross-family review gates, git-snapshot safety rails, and no server. Dogfooded.

MCAA (Minecraft AI Agent) is a Fabric mod that brings the power of Large Language Models (LLM) into Minecraft.

acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary, 25 providers, MCP server built-in.

Your personal AI, everywhere you are.

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.

A lightweight Grok plugin for Claude Code — delegate coding and review tasks to the Grok CLI. A simple reimplementation of OpenAI's codex-plugin-cc.

Telegram bot that runs Claude Code or OpenAI Codex on your VPS and streams responses back to chat. Supports project switching, sessions, voice, plan mode, and queues.

8 free AI automation workflows for n8n. Content repurposing, lead generation, email classifier, RAG chatbot, social monitor, client onboarding, web scraping, voice assistant. By Automatia BCN.

A hybrid RAG chatbot that answers financial and tax questions using structured data, regulatory documents, and AI-powered retrieval. Built with Django, FAISS, NetworkX, and OpenAI.

Autonomous AI-powered job search engine. Scans 139 companies, scores jobs 1-10, tailors CVs, preps interviews. Runs while you sleep. $0 AI cost.

An AI-powered tool that detects rooftops from satellite images, estimates solar panel potential and ROI, and provides smart recommendations using GPT

Run PAI (Personal AI Infrastructure) without an Anthropic subscription. Adapter layer for OpenCode — use any LLM provider.

This repository showcases a curated collection of the most useful and reliable free GPTs from OpenAI's GPT Store. Covering domains such as forensic analysis, mathematics, programming, SEO, document management, and education, each GPT has been thoroughly tested to ensure top performance.

Self-hosted alphaxiv-style paper-reading app (FastAPI CORS proxy + Vite/React/TS SPA)

A Windows-native tray utility for switching Codex OpenAI accounts and compatible providers without splitting the shared ~/.codex session history.

Open-source iOS workflow app and reference architecture for turning screenshots into structured AI insight cards.

A coding agent that keeps its state in a running program, not in the chat.

Universal AI API proxy — hot-switch between any LLM provider (GitHub Copilot, OpenAI, Anthropic, Z.AI, MiniMax, DeepSeek, Groq, Ollama, and more) from any AI coding agent (Claude Code, ForgeCode, OpenAI Codex CLI, OpenCode, Cline, Aider, Continue)

Android and iOS client for AI providers. Make requests directly to providers or secured through our API key protection backend.

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

Your AI that actually sees and does. A realtime desktop voice assistant that sees your screen, controls your computer, and gets things done, hands-free.

Production-grade Perplexity-like AI agent with real-time web search, ReACT/ReWOO/Reflexion/Tree-Search reasoning, MCP & A2A protocols, multi-agent orchestration, streaming SSE API, and full evaluation suite. Built with FastAPI, OpenAI, Anthropic, and Redis.

Transcribe audio and video offline with OpenAI Whisper on your device, keeping data private. Supports many languages with fast, fully local, reliable transcription. 🐙

AI-powered terminal-based Git assistant

Orchestrator for automated GitHub issue monitoring and agentic development across multiple repositories.

Pi extension for switching between multiple OpenAI Codex accounts

AI-Powered Kahoot Bot Auto-Answer Chrome Extension - supports every question type

Multi-agent AI runtime with OS-inspired primitives — job scheduling, DAG orchestration, memory, tool execution and real-time observability. Built with FastAPI, Celery, PostgreSQL and LiteLLM.

Tiny Zig 0.16 local AI assistant with OpenAI-compatible providers, memory, tools, Telegram, and WebSocket.

Drop-in AI chatbot SDK + React widget. 3 lines to integrate. 11 LLM providers with auto-failover. 13 URL-only adapters (Stripe, Calendly, PayPal...). Markdown knowledge. Apache 2.0.

Multi-agent VTuber + autonomous worker platform — pair a chatty Live2D/Spine VTuber with tool-running sub-workers, orchestrate autonomous tasks, and watch it all in a 3D city playground. 5 swappable LLM backends (Anthropic/OpenAI/Google/vLLM/Claude Code CLI). Self-hosted, Apache-2.0.

The workflow framework for AI-assisted development. Four operating modes, 25 golden rules, and anti-hallucination guardrails for 9 frameworks.

A complete social media operator's playbook — 37 skills, 12 functions, any agent. Agent-agnostic skill graph for X, LinkedIn, IG, TikTok. Works with Hermes, Claude Code, Droid, Cursor, OpenAI agents. Built by Crewm8 (crewm8.ai).

Free, browser-based BYOK AI website builder — v0 / Lovable / Bolt.new alternative. Bring your own key from 17 providers, generate & deploy full code, no subscription.

让 Claude Code 用 ChatGPT/Codex 订阅额度调内置 GPT Image 2 出图——不用 OPENAI_API_KEY、不计 API 费用 · A Claude Code skill: generate images on your ChatGPT/Codex subscription quota, no API key, no API billing

豆芽 Douya — 基于 llama.cpp 的隐私优先本地 AI 桌面助手 · 完全离线 · 多后端(CUDA/HIP/Vulkan/SYCL) · GPU 加速 · 多模态 · RAG · OpenAI 兼容 API

Open-source AI knowledge base & custom chatbot builder — production-ready Next.js SaaS with RAG, document upload, URL scraping, Q&A training, citations, and embeddable chatbot widgets. Stripe, credits, NextAuth, Prisma.

Transparent LLM gateway trace recorder · sub2api / CLIProxyAPI / new-api 的 LLM 网关流量录制器

GenPark/OpenClaw skill: Implement OpenAI & Stripe's Agentic Commerce Protocol (ACP) for capability negotiation, cart management, and Stripe Payment Token payments.

Drop-in observability for the OpenAI Node SDK. Wrap your client once and every chat.completions.create and responses.create call lands in Voight — prompts, tokens, cache reads, tool calls, latency, errors.

Self-hosted, open-source personal AI assistant — streaming chat with agentic tools, long-term memory, RAG, tasks & reminders. Go + Vue 3 + PostgreSQL/pgvector. AGPL-3.0.

🎙️ 本地播客/视频蒸馏工具：贴链接 → 转录·分章·摘要·五类亮点·双语字幕。Local-first (FastAPI + Vue)，可插拔多 LLM（DeepSeek / OpenAI / Claude / GLM / 通义 / 豆包 / Kimi）。

Use OpenAI Codex models in GitHub Copilot Chat with ChatGPT OAuth

Dr. Émile Telegram bot: AI emotional-support assistant with FastAPI backend, PostgreSQL, Redis, admin dashboard, and safety guardrails. Not a licensed mental health professional.

Template agents.md templates for use with OpenAI Codex

Personal finance tracker with AI-assisted categorization. Self-hostable Next.js + PostgreSQL + OpenAI.

remove ads from mp3 files

Open-source AI-powered B2B outreach system — lead scoring, personalized cold emails, reply tracking & auto follow-up. Built with N8N, OpenAI, GLM-4, and Google Places API.

一个基于 LLM 的 Bilibili 视频总结命令行工具。CLI tool to summarize Bilibili videos via subtitles or audio transcription using LLMs.

面向中文标书（MD）的混合抽取：规则/NER 优先，仅将低置信或冲突片段交给 LLM——可审计、低成本、高效率。Hybrid extraction for Chinese tender docs (MD): rules/NER first, LLM only for low-confidence/conflicts—auditable, lower cost, higher efficiency.

SkyPortal SDK & CLI - Open Source

AI-powered career assistant with XGBoost ML model (78.14% accuracy) trained on 6K+ resume-job pairs. Features advanced NLP skill extraction, GPT-4 resume enhancement, and intelligent job matching with real-time predictions.

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

Codex-Pro-Launcher is an external enhancement launcher for the Codex desktop application.

Agentic AI-powered security finding triage for DefectDojo

Local-first Agentic RAG knowledge base with hybrid retrieval, ReAct agent, Vue UI, Ollama/DeepSeek/OpenAI, MCP and Docker.

AI 跨境通 · 跨境电商 AI 内容引擎

Monitora a cota das contas Claude Code e Codex CLI e troca de conta automaticamente antes de bater o limite. Python stdlib puro, sem dependencia, sem servidor.

Docker stack: Open WebUI + LiteLLM + admin console — chat UI, OpenAI-compatible API, and ops panel for local & cloud LLMs in ~60 seconds.

AI customer support agent with semantic search — handles Gmail, WhatsApp & web via OpenAI Agents SDK + FastAPI

Local coding-agent control plane — MCP action governance + LLM-path protection + cost control. One Rust binary, no SaaS.

A self-hosted web frontend and SSH gateway for the official Codex app-server.

An agent runtime designed for tool-driven loop engineering.

P2P multi agent orchestration harness, universal automation system and IDE

A native Mac canvas for AI agent workflows. Four node types, MCP tools, and local models via Ollama — no account, no cloud, no telemetry.

One voice agent to control all your Claude Code sessions — drive them hands-free from your browser or phone.

Tail-aware scientific RVE diagnostics with a bounded optional OpenAI agent

MALLO (MultiAgent LLM Orchestrator) es un sistema avanzado de orquestación de múltiples agentes de Modelos de Lenguaje de Gran Escala (LLMs). Diseñado para manejar consultas complejas, MALLO utiliza una variedad de agentes, desde modelos locales hasta asistentes especializados y APIs de terceros.

"Local LLM agent framework in Rust — native tool-role support, tmux session persistence, two-tier summarization, and ShareGPT logging. Works with any OpenAI-compatible backend."

Readymade self-hostable backend server for chatbots. Built-in admin dashboard, sandboxed skill execution, MCP integrations, and generative UI via ProChat. Just point your chatbot at one Chat Completion API endpoint.

Single-line local context HUD for Codex CLI sessions.