Openai agents

Universal Python library for Structured Outputs with any LLM provider

Transform TypeScript classes into JSON Schema definitions with automatic support for OpenAI, Anthropic, and Google Gemini function calling (tool) formats

An AI-powered document assistant with multi-model retrieval system

Smart Search with GenAI is an AI-powered semantic search tool that delivers context-aware, summarized answers to natural language queries over structured data. It leverages Streamlit, FAISS, and Azure OpenAI for efficient vector search and LLM-based summarization.

A self-contained Google Colab Notebook that implements RAG using Postgres pgvector, pgai, and LLMs. Supports local-Ollama/OpenAI/Anthropic

A CLI RAG app for digging through the JFK files.

A Jupyter Notebook–powered toolkit that uses Retrieval-Augmented Generation (RAG) to help you craft a knockout resume. Feed it your raw career data (LinkedIn exports, old CVs, brag-worthy project notes), and let an AI do the heavy lifting—so you can spend your time practicing interview answers (or napping).

Robust Adaptive RAG algorithm for Lawyers

Snowflake-grounded natural-language chat agent over US Census data — guardrail → state resolver → hybrid metadata retrieval → structured plan + AST-validated SQL → self-check pipeline. Built as a 24-hour take-home in Next.js / TypeScript.

🍔 Automates a food order from a json food menu using Retrieval-Augmented Generation (RAG) with OpenAI and MistralAI.

A modern RAG framework for closed and open source LLMs built as a demo for the startup Brance.

LLM + RAG to generate answers about the manifestos of the parties for the 2024 Austrian legislative election

The Image Search Engine is a modern AI-powered web application leveraging Retrieval-Augmented Generation (RAG) to combine large language models (LLMs) with advanced image retrieval techniques.

Retrieval-Augmented Generation server with Pinecone and OpenAI

Lightweight RAG implementation for all your LLM endpoints

📈 AI-powered financial analyst with real-time stock data, SEC 10-K analysis, and LangGraph agents. Built with FastAPI, React, FAISS, and Yahoo Finance API.

Chat with your documents. RAG implementation leveraging OpenAI's GPT-4o and Text-Embedding-3-Small models.

Match synthetic patients to clinicaltrials.gov restAPI data with ChatGPT4. Course project for Johns Hopkins University EN.705.651.8VL : Large Language Models: Theory and Practice

Smart Context Optimization for LLMs - Reduce tokens by 66%, save 40% on API costs. Intelligent ranking and selection of relevant context using embeddings, keywords, and semantic analysis.

A FastAPI gateway for local LLMs that adds intelligent web research, multilingual recency/how-to detection, time-anchored guidance, context injection, and OpenAI-compatible SSE streaming. Turn any local model into a recency-aware, context-enhanced assistant instantly.

A chatbot for HealthWise Clinic that uses OpenAI and RAG for accurate responses, built with Next.js and Astra DB.

This project(RAG) focuses on operationalizing LLMs by integrating OpenAI, MLflow, FastAPI, and RAGAS for evaluation. It allows users to deploy and manage LLMs, track model runs, and log evaluation metrics in MLflow. The project also features MLflow traces that logs all the user inputs ,responses ,retrieved contexts ,and other essential metrices.

Make a crossword in a few seconds with ChatGPT's API

multi-headed intelligence for modern AI - a clojure agent system with dynamic tools and llm delegation

A lightweight Python agent framework inspired by Gemini CLI, with tool calling, MCP integration, skills, memory, and human-in-the-loop approvals.

Terminal AI agent with ReAct pattern - execute shell commands, run Python, analyze images. Supports Gemini, OpenAI, Ollama.

A Deribit trading terminal with Vida, an AI copilot that analyzes options, builds spreads, and places smart orders.

macOS and iOS clients for self-hosted Hermes Agent API Server: streaming chat, Responses, Runs, tool progress, and Cron Jobs

LLM-driven chess agent with three modes — Battle (you vs AI), Teach (AI-generated lessons), Watch (LLM vs LLM). Plug in OpenAI / Gemini / Claude side-by-side. Voice chat with character personalities + emotional TTS. LangGraph state machine. Optional Interbotix RX-200 robot arm + RealSense camera for physical play.

rowser-based AI coding assistant — zero install, zero deploy, zero config. Agentic loop with 10 tools, 18 skills, and a force-directed Cosmos visualization. Runs entirely client-side.

Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent PTY shells, sub-agents, planning, hooks, prompt caching, rate-limit-aware retry, mid-turn-checkpointed sessions. Anthropic + OpenAI.

Production-Ready AI Systems • Enterprise Architecture • Azure & Beyond

StoryGPT generates fictional narratives using a simple multi-agent pipeline with OpenAI API

Orchestrate agent teams across multiple AI coding CLIs (Claude Code, Codex, more via PRs). Define once, run everywhere.

A bare-bones Swift agent runtime with built-in tool execution, skill support, conversation-state handling with a unified multi-provider LLM layer (OpenAI-compatible/Responses, Anthropic, Gemini, and MiniMax, plus codex OAuth)

Extract notation tables from arXiv papers using LLMs.

Documentation for Cycles — AI agent governance, runtime budget, action authority, MCP integration

Smart pharmacy assistant for ViaPharma customers. Provides personalized OTC product recommendations based on symptoms using medical AI and safety-first approach.

🦀 Secure, fast and Ultra-lightweight personal AI assistant in Rust. Alternative to OpenClaw

The AI companion for the pull requests your AI writes. Review, summarize, explain, document, test & triage PRs and issues from a comment (aido <command>) or automatically on AI-authored PRs — with Gemini, ChatGPT, Claude, or any OpenAI-compatible model (Mistral, DeepSeek, …). BYO key, no third-party data processor.

This Discord bot uses OpenAI's API to generate human-like responses in chat conversations.

AI emotional support and study assistant for students, with FastAPI web UI, local demo mode, and OpenAI/DeepSeek-compatible integration.

Sovereign Local AI Workspace & LLM Runtime Manager. Easily Run GGUF, MLX, OpenAI, Gemini, etc. Under One Unified Interface ✨

OpenClaw in 815 lines: a personal AI assistant where every capability is a Markdown file.

Catch LLM cost changes in code review. Infracost for LLM spend.

Multi-provider LLM pipeline + open benchmark measuring when each frontier model runs out of distinct ideas. 10 LLMs, 16× cost-per-unique-idea spread for the same shipped quality.

Local-first key custody and policy routing for AI apps. Set keys once, route across providers through one OpenAI-compatible endpoint.

The shared AI foundation for TYPO3 — one LLM setup for every extension on your site

CLI that turns natural language into shell one-liner commands using an LLM.

Multi-provider LLM gateway with automatic fallback and cost tracking. Single API across DeepSeek, Gemini, OpenAI, and Anthropic.

An AI agent that lives in your terminal and codes for you.

💰 Optimize your Claude API usage to save 50-90% on costs with batching techniques and efficient request management.

UniversalLLMAdapter class initializes the appropriate client based on the specified provider.

A post-human AGI alignment blueprint co-developed with GPT-4o "Chappie" 😉

Visual AI canvas for building & testing Next.js UI components — supports OpenAI, Anthropic, and Google AI with node-based data pipelines.

Open-source Claude Code + OpenAI Codex (ChatGPT App) analytics and Discord Rich Presence. Factual cost, cache, context, and plan telemetry. Native Tauri, 100% local.

Headless multi-provider LLM agent runtime. Single Go binary, 16+ providers, 59+ extension hooks, zero opinions.

A curated library of 100+ battle-tested AI agent definitions across 15+ categories. Copy-paste ready for any LLM — OpenAI, Claude, Gemini, Llama, and more.

Give your AI coding assistant full programmatic access to Google NotebookLM — with per-project notebooks, session wrap-up, and cross-platform support for Claude Code, Cursor and OpenAI Codex.

Turn a short prompt into one clean, hand-drawn concept illustration starring a deadpan peanut — an agent skill for Claude Code and OpenAI Codex.

👨‍🏫 A smart multi-agent system that creates personalized learning programs, roadmaps, curated resources, and hands-on exercises using AI + Google Docs — in one click.

an opensourse AI coding agent

Scriptable, multi-provider AI agent for the terminal — pipe into it, script it, run it on any model, cloud or local

AI 軟體工廠：用一句白話需求，產出可審查的靜態網頁／小工具草稿（zip 或草稿 PR），全程人類把關。

🐾 OpenClaw 图形化管家 - 一键安装配置OpenClaw AI Agent，支持 30+ AI 模型（OpenAI/Claude/Gemini/通义千问/智谱/Moonshot），接入 22+ 消息平台（WhatsApp/Telegram/Discord/Slack/飞书/企业微信/QQ/钉钉），全程无需命令行。

WWA Transform — Turn any website into an AI-powered agentfront. Claude Code plugin + Codex agent + CLI.

AI-powered customer support agent built with Python smolagents and InterSystems IRIS — SQL, RAG, and live interoperability

Educational Python coding agent built from scratch to explain agent loops, tool calling, code editing, bash execution, permissions, context management, and OpenAI/Gemini providers.

A universal, highly intelligent LLM API proxy gateway. Seamlessly translates heterogeneous AI protocols (OpenAI, Anthropic, Gemini) with built-in multi-account rotation, circuit breaking, and zero-config deployment.

Community template: Wire Sendblue iMessage to any AI agent (Hermes, OpenAI, Ollama) via n8n — with fallback, Redis retries, and Telegram alerts. Deploy on a single VPS in 15 min.

统一的 AI 编程助手 Web 平台（Claude Code、Pi Agent、Codex）。实时流式输出、分屏并行、Agent 切换 Unified web platform for AI coding assistants (Claude Code, Pi Agent, Codex). Real-time streaming, split-screen parallel mode, agent switching, dark theme

Open source AI agent framework to build the future of data operations.

A practical cookbook of 10 Advanced RAG techniques — Naive, Hybrid, HyDE, Fusion, Parent-Child, RRR, Contextual Compression, and more. Working code + real benchmarks + plain-English explanations.

Multi-agent research copilot that separates LLM generation from deterministic citation verification — HALLMARK F1-H 0.747 (full dev_public, N=1119). LangGraph pipeline with a failure-driven controller loop, evidence-grounded Critic, and local PDF RAG.

Agent skill + CLI for multi-agent adversarial review of plans & specs before you execute them. Runs on the Claude Code / Codex subscriptions you already have — no API keys.

Compose agents like plain values. A TypeScript toolkit that wires LLM calls, tools, and functions into typed steps over eight providers. No framework, no ambient state.

Multi-agent AI crew that researches a stock and writes a cited investment brief.

Daily multi-agent OSS PR triage on GitHub Actions — analyzer + CI deep-dive + drafter + self-review critic. Microsoft Agent Framework on Azure OpenAI.

Neutral interop + governance layer for multi-agent systems. Any protocol in, any protocol out, with identity, budgets, and a tamper-evident audit trail.

🤖 Automate trading on Polymarket with AI agents to enhance your strategies and maximize your opportunities.

Autonomous multi-agent coding framework that plans, builds, validates and document software for you

“拼好会”是一款基于RAG的智能会议辅助系统，支持实时语音识别、英文会议翻译、会议纪要生成与 AI 辅助发言。系统可同时捕获电脑音频与麦克风输入，对会议内容进行低延迟流式识别，并结合RAG技术检索导入的 PDF、PPT、Word 等会议资料，为用户提供上下文相关的发言建议与内容总结。 项目支持 OpenAI、DeepSeek、Gemini、Qwen 等多种大模型，可用于英文会议、学术讨论、项目汇报等场景，帮助用户“听会、记会、翻译会”，提升线上会议效率与信息整理能力。

`MindMatrix.io – Freemium AI SaaS Toolkit for Creators & Freelancers | Text Gen, Resume Builder, Content Tools | Python + PHP + OpenAI/HF APIs`

Fix the JetBrains AI Assistant + Google Gemini "Something went wrong" error. A zero-buffer FastAPI + httpx proxy for the OpenAI-compatible (BYOK) provider: strips IntelliJ's model-id prefixes, returns a clean /models list, filters unsupported params, and disables Gemini 2.5 thinking to beat the commit-message streaming timeout.

Local AI Linux terminal assistant written in Bash. Explain commands, analyze files and logs, and use local LLMs or OpenAI-compatible APIs.

AI-powered real estate chatbot (OpenAI Assistant API + Streamlit): natural-language property search with AI-generated SQL. Live demo, 94% query accuracy.

This production-ready AI system automates customer support with multi-step workflows, tool integration, stateful conversations, and real-time performance monitoring.

Control the ChatGPT Desktop App on macOS via CLI to turn your subscription into a programmable AI backend for MCP clients.

ChatGptClone is a clone of OpenAI's ChatGPT virtual assistant, built using Python and the openai api

RPG Discord bot powered by GPT models

SoulLink - AI Soul Companion | Personalized AI chat with personality-driven interactions, multi-model support (GPT-4o & Gemini), tarot personality system

Autoresponed to whatsapp messages with openai API ChatGPT.

🏛️ Delphi is a versatile and adaptable conversational agent framework that streamlines chatbots and AI-driven agent systems.

Daily Telegram channel digest with OpenAI summarisation and pluggable Markdown output adapters (Notion, Obsidian, Logseq, Hugo, files, stdout, custom).

Safe-by-default AI agent. Gates every action through Authensor before it executes.

A CLI tool for querying OpenAI-compatible endpoints with a prompt and input file

An open-source tool to extract subtitles (.srt/.vtt) from Douyin video links via OpenAI-compatible ASR APIs. Supports batch processing and 1-click Docker deployment.

AI research assistant for prosthetics, orthotics & rehabilitation robotics papers. RAG pipeline with streaming citations, structured summaries, terminology extraction, and paper comparison. Built with Next.js 15, Claude, pgvector. Includes observability tracing and DeepEval evaluation pipeline.

Image and video understanding + generation for AI agents -- across Gemini, OpenAI, and Grok.

Deploy an API built with Streamlit on Heroku, in order to classify images.