Openai agents

一个基于大模型的 AI 面试准备助手（AI Agent），支持从岗位 JD 分析到多轮模拟面试、实时评分与总结报告，帮助求职者系统化提升面试能力。

Self-hosted, Docker Compose based AI agent orchestration: ReAct runtime, multi-adapter chat (Telegram / web), skills, memory with encrypted secrets, model benchmarking, and distributed userdocker work nodes.

A small, clear, and extensible multi-user Web Agent — chat, call tools, operate a workspace, browse the web, search for information, with each conversation running in an isolated sandbox.

Drop requirements docs → AI agents debate → structured specs with @implements in 7 languages.

Provider-agnostic Python library for composable LLM execution patterns, including consensus, refinement, ReAct tool loops, structured output, and budget-aware calls.

An auto-updating AI Model Catalog available as a CLI Tool, HTTP Server w/ SDKs, or Golang Package.

A Claude-Code-Desktop–style coding agent tab for self-hosted Odysseus. One-click install, zero-risk add-on, works with any API or 100% local.

AI-powered Chrome extension that translates web pages in place using Gemini, OpenAI, and Anthropic APIs

Branch, explore, and run code inline — an infinite spatial canvas for AI conversations. Supports Mistral, OpenAI, Anthropic, Gemini, and local Ollama.

An open-source, Zero-SDK LLM Billing Proxy & Credit Gating layer for AI startups. Intercepts completion requests, counts tokens, manages user credit wallets in SQLite, and provides self-healing model fallbacks

Ultra-low-latency reverse proxy that repairs truncated & malformed JSON in LLM streaming responses (OpenAI, Anthropic, Vertex AI, Bedrock) — fixes JSONDecodeError / serde_json EOF on truncated tool calls.

Go proxy enabling Cursor to use DeepSeek V4 (Pro/Flash) via OpenAI-compatible API. Supports zero-config thinking mode and multi-turn reasoning_content bridging.

Route Claude Code, Codex, and Copilot work across installed model CLIs with delegation guardrails and an observation-driven routing ledger.

The grok-build harness, unshackled: bring your own models (Anthropic, OpenAI, local LLMs) and pay for exactly the tokens you use.

AI coding agent inside the Godot editor — a Copilot/Claude-style chat dock that reads, writes, and debugs your project. 15+ LLM providers, inline diffs, runtime error capture.

A small, fast AI coding agent for your terminal. Bring your own model — Ollama, llama.cpp, LM Studio, OpenAI, OpenRouter, or any OpenAI-compatible endpoint — or use the hosted xShellz models. Single static Go binary, no API key required.

Local-first terminal AI agent with a lean, in-house runtime, TUI, MCP/OAuth stack, provider streaming, and durable sessions.

Trading agent that learns from his mistakes

Desktop AI chat app unifying local Ollama models with OpenAI and Claude — includes an agentic mode where the model can read/write files and run shell commands, with every action requiring your approval.

OpenAI-compatible media generation gateway for AI Agents. Supports multi-provider image/video generation, model routing, prompt enhancement, and built-in Web Studio.

Native macOS agent harness with permissioned tools, local LLM support, real document generation, and inspectable Markdown memory.

强模型规划+弱模型执行+程序验证的编程任务调度系统。强模型只动嘴，弱模型干脏活，token 省约 60%。

Self-hosted AI agent framework with permission modes, audit logging and MCP. Runs on your machine, in Docker, or on a Raspberry Pi.

Voice-controlled macOS companion that talks back, points at UI elements, and can drive your Mac end-to-end ; making MacOS an AIOS.

🤖 Enhance coding with Claude and Codex, a library for duo peer programming that combines AI strengths for superior code generation and reviews.

Codex-native operating layer for repeatable AI workflows with AGENTS autoload, project-isolated memory, plugin skills, and a thin ro CLI for terminal + VS Code chat.

A science inference cluster — every model, from protein folding to LLMs, behind one OpenAI/Anthropic-compatible endpoint and a single key. Built to run beside HPC so agentic AI researchers can drive simulations and model inference together. Self-deploying on RKE2 with KServe/Knative + HAMi GPU.

Browse open-source tools for automating scientific research, from literature review and experiments to writing and peer review

AgentVoir is an open-source enterprise AI agent registry, LLM gateway, model proxy, semantic cache, and governance control plane for agentic AI systems.

10 copy-paste superprompts + 100 agent-ready goals for ChatGPT connectors (Gmail, Drive, Calendar), Claude Code, Codex, and MCP agents. Authored with Claude Fable 5, executed by GPT-5.5 xhigh or cheaper models. Includes LOOPS.md-inspired agent-loop templates.

Open-source autonomous trading bot for Robinhood Chain. Four strategies: launch sniping, momentum, Stock Token premium/discount arbitrage, and a bring-your-own-key LLM strategist (Claude, OpenAI, Groq, or OpenRouter). Real risk caps, real signed swaps, paper mode by default, live P&L dashboard.

Research on why autonomous AI agents don't know when to stop, and three engineered fixes.

Developer-first AI chat workspace for comparing multiple language models side-by-side in real-time. Features multi-model streaming, custom provider integration, token analytics, personalization, and skills registry with terminal execution. Built with Next.js, TypeScript, and MongoDB for reliable, fast model evaluation and prompt engineering.

Develop accessible ChatBot with Azure OpenAI and Streamlit

KleanBot, A Modern Android Chatbot App using OpenAI, MVVM, and Clean Architecture with Kotlin.

🤖 Bots framework and sample chatbots for Ethora. Structured as a monorepo with a reusable bot framework. Features: • Modular bot framework for easy bot development • OpenAI GPT integration • Real-time XMPP messaging • TypeScript support • Easy deployment. Tech: TypeScript, XMPP, OpenAI API

A simple chatbot built using OpenAI's GPT-4o-mini.

AI Camera is a smart image recognition system built using an ESP32-CAM, I2C LCD, and a button trigger. On pressing the button, it captures an image, sends it to OpenAI’s Vision API through an n8n workflow, and displays the identified object(s) on the LCD screen and Serial Monitor. It’s a compact and low-cost AI-powered vision device.

WebScrapeSummarizer 🌐✍️: A web tool that fetches and summarizes content from any domain, offering insights in a compact CSV format.

Build a low/no code ChatGPT application under 20 minutes with Zoho Creator.

Resigned Yann-LeCun

Virtual phone assistant powered with an LLM

The future of AI is speaking Chilean, cachai?

A natural-language interface for your 🐚 shell, powered by GPT 🤖

A comprehensive Express.js application with OpenAI integration for generating brand stories and assisting with branding for regenerative, conscious businesses.AI-powered brand storytelling, and more.

Multiple choice quiz generator built in React. Generate quizzes for any topic using AI. Intended for offline use with personal API key, URL is meant for UI demo purposes.

Collection of 100+ battle-tested LLM prompts for coding, writing, and analysis. Works with GPT-4, Claude, Gemini. Copy-paste ready.

Get reliable legal information and guidance related to Philippine law from our AI-powered platform. We provide general legal information on various areas of law, including Employment Law, Property Law, and more. Contact us today for assistance with your legal questions.

Developer infrastructure for discovering and comparing LLM models and providers

Life-Coaching AI (Flutter): A cross-platform mobile app that provides personalized life coaching through AI. Users can set and save personal goals with secure, private access.

Unified AI model gateway built with Node.js + TypeScript. Accepts multiple API formats and routes to different LLM providers.

The agentic browser for your AI apps and agents, with built-in MCP and A2A support.

A unified OpenAI API wrapper module for ErisPulse | OpenAI 通用接口封装模块

Allows to easily run local REST API with a custom LLM, running locally or remotely, with user defined system instructions. Useful for quick local autmations that require problem solving with large langague models and interaction via a REST API.

AI Voice Chat

An app for creating, managing, and sharing AI assistants, vector stores and related tools.

AI game asset generator — create images, documents, scripts, and download as a complete game plan via OpenAI

Lightweight OpenAI/OLLaMA/GenAI compatible caller, originally designed for DeepInfra.

A Model Context Protocol (MCP) server implementation for Cisco NSO that enables AI-powered network automation through natural language interactions.

Modern AI-powered text processing platform with customizable summarization, translation, grammar checking, content expansion, and tone adjustment features.

Twilio Conversation Relay 機能を使って、WebSocketベースのリアルタイム音声通訳をデモするアプリケーションです。

TypeScript-based Model Context Protocol server with SQLite. Enables AI to persist and search user entities, observations, and relationships.

real-time and file-based speech-to-text desktop app powered by OpenAI Whisper with a modern Flet GUI

Use Claude Code with ChatGPT/Codex, OpenAI, GitHub Copilot, Gemini, OpenRouter, Anthropic, or custom backends. A single-binary Rust gateway with OAuth, smart model routing, virtual 1M context, and built-in TUI observability.

Web app to decide what meal to make with your ingredients, and tells you how to make it step by step with integrated AI.

AI-powered README generator that creates beautiful, professional documentation for your GitHub repositories

This is an unofficial python wrapper for chatgpt images 2 api (aka GPT Image 2.0 API)

AI-powered LinkedIn post pipeline — multi-agent research and writing with n8n orchestration, Claude, GPT-4, and Google Sheets approval loop.

A robust, transparent REST API proxy service for LLM APIs with profile-based configuration and comprehensive logging.

Subscription free, privacy first, AI-native health companion app for smart rings

Unified TypeScript SDK for LLM providers (OpenAI, Anthropic, xAI) with streaming, structured outputs, and zero dependencies.

A React Native app that allows users to extract text from images, PDFs, and audio using AI-powered OCR and transcription technology. The app features a queue-based job processing system with automatic polling, markdown rendering for rich text display, user authentication, camera functionality, PDF document Q&A with multiple AI model

OpenAI-compatible API server wrapping Claude Code in headless mode. Use Claude via any OpenAI client.

Deprecated: development continues at Agentryx-ai/pass-the-thread.

Drop-in Agent Skills, subagents, output styles, hooks & config templates for Claude Code (~/.claude) and OpenAI Codex CLI (~/.codex). Copy, restart, done.

GhostPour — Open-source LLM API gateway with auth, multi-provider routing, and subscription-based access control. The invisible hand for your iOS app.

Open-source AI gateway and operations platform. Bring your own provider API keys and unify every AI model behind a single OpenAI-compatible endpoint with production-ready routing, analytics, backups, restore, clustering, team management, and enterprise-grade operational tooling. Self-host in minutes or run with Nexus Cloud. To follow on X: https://x.com/alayranexus

Gives LLMs precise answers from pre-researched code across repositories and languages - instead of re-scanning files and rebuilding context every session

CLI for peak AI inference performance. Analyze code for latency, throughput, reliability issues. BYOK mode.

A native desktop client for free access to Claude Mythos AI across Windows, macOS, and Linux.

A deterministic gate for AI-proposed actions: the model suggests, your constraints decide, nothing executes unapproved.

🚀 LLM API Gateway with Intelligent Cache Optimization. Reduce LLM API costs by up to 90% through structural request optimization and vendor KV cache maximization. Built with Go.

Caveman prompting, measured. A two-channel evaluation protocol scoring what input and output compression actually cost LLMs in dollars, accuracy, and surface-text fidelity across seven models and five benchmarks.

Self-hosted Question → Search → Answer workspace with explicit control over AI providers, models, search, MCP tools, and run data.

Independent OpenAI-compatible local relay for your own ChatGPT and Claude subscriptions: one standard /v1 API (chat completions, responses), multi-account balancing with automatic failover and retry, and a cross-platform desktop app. Single-user personal use; not affiliated with any provider.

Local-first AI protocol gateway and model router for OpenAI, Anthropic, and Gemini APIs

🧠 it remembers what your company forgets - an brain that measures itself and patches its own gaps.

Natural language to shell commands with local LLMs. Rust TUI: press Ctrl+K, describe the command, get the exact incantation — Ollama by default (fully private), Claude/GPT optional. Sub-500ms, daemon-backed, with built-in destructive-command warnings.

WordPress plugin combining multilingual routing, SEO meta tags, and AI-powered content tools — language detection, URL routing, hreflang, meta descriptions, and AI translation/generation via Anthropic, OpenAI, or Gemini.

Desk display showing Claude Code & Codex usage limits (5h/7d) on a Waveshare ESP32-S3 round AMOLED. LVGL firmware + Python host bridge.

Python Discord bot framework — slash commands, plugins, versioned config schemas, middleware, AI orchestration, and 30+ guides. Supports Claude, OpenAI, Gemini, Groq, and more. 1500+ tests. Production-ready.

Local AI Workstation CLI for LM Studio/Ollama. SysAdmin, NetAdmin, and Senior Dev in your terminal. Maps codebases, previews edits, autonomous build recovery. Deep-kernel health, crash logs, and network stack. 54-voice TTS + Hybrid BM25/Semantic search with PageRank graph and heat-weighted memory. Windows-first. One Rust binary. No cloud. No API.

🚀 Get smarter financial decisions with AI: multi-LLM support (Ollama, Gemini, OpenAI), natural conversations about your finances, automated portfolio recommendations, and 10-year historical insights.

Delibera - Thoughtful AI Decisions. A framework for collective decision making through structured AI deliberation. Supports multi-model councils with RAG (Qdrant, PgVector), debate strategies, Knowledge Keeper, Chairman roles, dependency injection, and context compression.

Enterprise intelligent customer-service orchestration with Spring AI, Dify knowledge, and pluggable local/cloud LLMs

Local-first AI document-intelligence desktop app for Windows (.NET 8 / WinUI 3). Turns your documents into a queryable, RAG-augmented knowledge base — HNSW vector store, hybrid semantic/lexical search, HyDE, LLM reranking. Built-in local Llama 3.2, Ollama, and opt-in OpenAI/Anthropic. No telemetry; local by default.

🎬 工业级 AI 编剧工作站（小说转剧本）：基于 FastAPI + Vue3 架构，首创「双路 RAG 长期实体记忆仓」与「LangGraph 多智能体有向图拓扑编排」技术。支持 EPUB 智能解构、长文本跨时空剧情锁、多通道 SSE 异步流式渲染，将长篇小说全自动、高颗粒度重塑为符合电影工业标准的标准分镜脚本。

可视化 AI 工作流画布 — 通过拖拽节点构建 AI 工作流，支持多模型、知识库、API 集成。Codex 插件 & OpenAI 兼容 skill。

Stop paying for API credits twice. Luna bridges your existing premium AI subscriptions apps into a seamless, OpenAI compatible local gateway

Native-Swift coding agent for the terminal and ACP. One binary, no Node runtime — customizable tools, parallel agentic workflows with capability-based model bindings. macOS, Linux, and WSL, down to a Raspberry Pi.