Openai agents

The modern, local-first PostgreSQL client with a natural-language SQL assistant.

Benchmark LLMs on your own codebase. Repo-specific probes, blind rubric-based judging, and correctness-first rankings.

Minimalist coding agent harness with a Textual TUI and headless CLI. <1k-token system prompt, 18+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 52 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard

Domain-specific AI skills for working with Valkey - reusable knowledge packs that help agents and developers write correct, idiomatic, high-quality code against the Valkey ecosystem.

Daily tracker for frontier AI lab papers, model cards, system cards, and technical reports

TAI Chief - The only AI Chief of Staff platform that every CEO will ever need.

Build real websites using natural language - no coding required

⚡Switch LLM Providers for Any Apps with One Click: A Single-Binary LLM Gateway with Auto API Translations and Traffic Inspections.

⚓ Provider-agnostic terminal privacy first coding agent — bring your own model. Switch between OpenRouter Anthropic, OpenAI & local Ollama with one command. Plan mode, checkpoints, MCP, hooks, sub-agents and a modal prompt, built off Pi.

Computer Use Examples with API Integration Full Stack

Self-hosted AI roleplay client with memory that survives long campaigns — tiered canon/heuristic/reflex writes, retrieval-time privacy ACL for group chats, and native MCP tool support. Imports v2/v3 character cards. Runs on Ollama, OpenAI, Anthropic, OpenRouter, or any OpenAI-compatible endpoint.

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

5 Best Free OpenClaw Android AI Agents 2026 – No Root Full Linux

Multi-session coordination for AI coding agents (Claude Code + OpenAI Codex) — file locking, crash recovery, and cross-session task delegation. Pure Bash hooks, no server, no daemon.

Claude Code plugin that routes heavy coding tasks from Claude to OpenAI Codex (GPT-5.6) as a supervised background worker — Claude briefs, delegates, reviews, verifies.

Stop replaying the transcript: capsule session state + rolling memory for LLM CLIs (Claude Code, Codex). Measured: −90.3% vs no-cache / −30% vs cached replay at turn 10, reproducible bench. MIT, provider-agnostic.

A fast, model-agnostic coding agent for your terminal — built in Rust with a rich TUI, MCP, lossless context, safe tools, and built-in verification.

Self-hosted AI agent that researches US market news on a schedule and publishes structured briefs to a terminal-style dashboard. Bring your own LLM.

Scaffold and manage plugin marketplaces for Claude Code · GitHub Copilot · OpenAI Codex · Cursor, distributed through any Git host

Self-hosted EVE Online AI assistant for Telegram, Discord, and CLI — EVE SSO/ESI, local SDE, and OpenAI Responses API.

Self-hosted LLM gateway + model router. One static binary, OpenAI & Anthropic dialects in, any provider out, zero telemetry.

High-performance Rust proxy that translates Anthropic Messages API to OpenAI-compatible format, routing to NVIDIA NIM, Ollama & OpenRouter. Built with Tokio + Axum.

Open-source LLM cost monitoring & optimization platform. Track spend across OpenAI, Anthropic, DeepSeek & OpenRouter in real-time.

Open-source stock breakout signals: 8-source harvest, AI scoring, pump-and-dump filter, LightGBM backtesting on historical scans. Next.js, PostgreSQL, Docker self-host, agent API & x402.

Single-binary LLM gateway (gw) in Rust — OpenAI/Anthropic-compatible APIs, multi-provider routing, per-key auth/quotas/rate-limits, failover, streaming, and a billing ledger

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.

A tiny native macOS menu bar app for monitoring Codex usage - no browser extensions, no Chrome access, no Keychain access, no telemetry.

Inja LLM Gateway — stateless OpenAI/Anthropic API gateway with multi-provider routing and usage hooks.

Use Claude Code 100% free with 100+ NVIDIA NIM models via LiteLLM proxy. No Anthropic subscription needed. Works on Windows & macOS.

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings — with the widest weight×KV quantization matrix of any MLX server. No Python, no GGUF.

璇玑 Xuanji —— Go 单二进制 AI 网关，OpenAI / Anthropic 双协议汇聚。one-api / new-api / LiteLLM 轻量替代品，自动分流、负载、重试，成本优先路由，高可用不中断。

A Java library to create reliable agents

SOC agent that ingests security logs, detects attacks mapped to MITRE ATT&CK, and uses an LLM grounded in a RAG knowledge base to analyze and recommend remediation, with human approval and rollback built in. FastAPI/Postgres backend, React frontend. Runs fully offline, no API keys needed.

Apple-native cloud-hybrid RAG client for PDFs and personal files using SwiftUI, Vision OCR, OpenAI embeddings and Responses API, and Pinecone vector search.

OpenAI Codex 한국어 AI 개발 파트너 페르소나 플러그인. 15관점 검토, 20개 트리거 패턴, 투자/법률/회계세무/마케팅 도메인, 인터뷰형 생성/편집. Apache-2.0.

Free and open-source production-grade RAG platform that converts documents into conversational AI assistants. Enable private deployment for data security. Features hybrid retrieval, multi-tenant isolation, streaming chat, auto document parsing, visual Agent & ingestion pipeline canvas, GraphRAG and automatic memory.

OpenPawlet (PyPI package name open-pawlet) is a single-process web console for the OpenPawlet ecosystem. It exposes an HTTP API, a browser UI, an OpenAI-compatible /v1/* surface and the embedded agent runtime

GabyT is LLM platform with OpenAI

Multi-agent system built with .NET 10 and Microsoft Agent Framework that orchestrates specialist agents for database querying and file exporting (Excel, Word, PDF) via Azure OpenAI.

High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.

A comprehensive Python toolkit for LLM integration with chat, embeddings, and reranking. Supports Azure OpenAI, local models, async operations, memory management, and response caching.

Starferry is a FastAPI-based API service that generates custom bingo game items using multiple AI providers. The service accepts prompts from users and returns 25 bingo items generated by the selected AI model (OpenAI, Google's Gemini, or Grok).

The Toolpack SDK is a unified TypeScript SDK for building AI-powered applications. It provides a single, consistent API to work with multiple AI providers OpenAI, Anthropic, Gemini, and Ollama without vendor lock-in.

Agentic PDF content translator, delivers perfectly formatted documents.

Multi-layer AI agent system for intelligent infrastructure management. Features AI Terraform code editor with BYOK (Bring Your Own Key), Model Context Protocol (MCP) server with 45+ tools, and self-deploying Kubernetes observability agents. Supports OpenAI, Anthropic, and Azure OpenAI.

AI desktop agent with full PC control. Single Go binary + Tauri desktop app.

Guidance and xUnit samples for evaluating .NET AI agents with AgentEval — stochastic tests, red-team scanning, trace replay, memory benchmarks, and CI templates

OpenClaw, but safer and better. Optimized for whatever app you have.

Chat With Documents is a Streamlit application designed to facilitate interactive, context-aware conversations with large language models (LLMs) by leveraging Retrieval-Augmented Generation (RAG). Users can upload documents or provide URLs, and the app indexes the content using a vector store called Chroma to supply relevant context during chats.

面向个人自动化工作流的消息中转服务：统一消息事件、路由和生命周期记录，支持微信/API 入口与本地/HTTP Agent 处理器。

Real-world patterns for shipping AI agents to production. Learn versioning, cost optimization, multi-tenancy, guardrails, and observability through runnable TypeScript examples.

AI-powered coding assistant for the command line. Uses OpenAI Responses API (not Chat). Autonomous agents, parallel code reviews, 33+ tools, multi-model support. Built with Bun & TypeScript.

Central repository for the reShapr project community health assets.

HTTP shim for injecting MCP tools into OpenAI-compatible chat completions

Iris Agent is a lightweight, flexible framework for building AI agents in Python. It simplifies the process of creating agents that can use tools, manage memory, and interact with various LLM providers.

Multi-provider AI usage monitor with real-time dashboard, desktop pet overlay & ESP32-S3 hardware companion — tracks Claude, OpenAI, DeepSeek, Ollama and LM Studio. Expanded from the original Clawdmeter project.

CODEX-R: codex -r for Claude Code sessions

AiAgentEconomy for wallet with .Net 9 - SemanticKernel - OpenAi

֎ Simple, privacy-first web UI for local LLMs (Ollama, LM Studio, OpenAI-compatible APIs)

MirrorBuddy - La Scuola Che Vorrei: AI-powered educational platform with voice tutors for students with learning differences

Voice-based mock interview platform featuring intelligent conversation management and time-aware stage transitions

AI Native Semantic Language

Modular CLI for distributing 50+ AI agent skills across multiple coding assistants

An advanced AI-driven code analysis tool built with Next.js, leveraging OpenAI's API to review and debug code efficiently.

Cache-aware orchestration for LLM agents. Fork helpers that share cached prefixes, detect cache breaks, and cut token costs by 38%+.

AI-powered self-hosted media automation agent — replace your entire arr stack with one intelligent pipeline

NV Digital Open Operator System (NV oOS) is an Object-Oriented AI framework for WordPress connecting your data with OpenAI, Gemini, Anthropic, DeepSeek, Hugging Face, Cloudflare, OpenRouter & Ollama (Local) models. Create & manage AI Assistants that can interact with users, access WordPress (API) data, & perform as a MCP Server & Chat Agent

Anyany.js is a Node.js-based generative AI framework for software testing, supporting both local (Ollama) and cloud (OpenAI) models

🧠 Drupal DevOps Co-Pilot — an open-source AI assistant that automates Jira, GitLab, Drush, and EC2 deployments using FastAPI and Ollama. From issue to deployment — faster, smarter, auditable.

A Model Context Protocol (MCP) TypeScript template with multi agents that can send Emails, schedule meetings and answer knowledge-base related questions.

A programming language for AI agents. Type-safe. Parallel. Observable.

Modern cloud-native Agency Management System (AMS) for insurance agencies

Superpowers agentic skills framework adapted for OpenAI Codex CLI. Part of the FX Studio AI cross-platform suite.

Aiyu Multi-Agent - Lightweight AI Agent Framework with Tools, Plugins, and Multi-Agent Orchestration

A framework for resonance-based decision-making in artificial agents, combining celestial influences, memory feedback, and symbolic emergence.

This repository is packed with practical, beginner-friendly codelabs that bring AI and coding concepts to life. From extracting job applicant details with OpenAI’s Function Calling (think resume parsing into JSON) to automating real-world tasks, you’ll find working code, sample datasets, and step-by-step guides here.

.NET 10 console app showcasing a RAG agent with query reformulation, contextual search, streaming responses, and source citations built with Microsoft Agents AI and OpenAI.

Portable_TA is a lightweight, OpenAI-compatible LLM service that acts as an always-available AI Teaching Assistant. It provides document-grounded answers using RAG, maintains conversation memory, and integrates easily with tools like OpenWebUI for fast, portable, and intelligent student support.

LLMWorkbook is a Python package that integrates Large Language Models (LLMs) with tabular datatypes - workbooks and dataframes for seamless data analysis and automation.

Token-optimized AI agent runtime with 12 providers, multi-agent DAG, TOON compression & encrypted vault .

Multi-agent RAG system with a Supervisor architecture — search, ingest, and manage knowledge bases via natural language.

🏛️ AI team debates in your terminal. Multiple expert personas discuss, challenge each other, and reach a decision.

NFlow is an intelligent document processing and knowledge management system that leverages vector embeddings and natural language processing to extract, organize, and query information from various document formats.

Generative AI Apps Practices – A curated suite of hands-on generative AI projects showcasing best practices in prompt engineering, code repository interaction, legal document summarization, and financial statement analysis.

🧠 Conduct advanced research using a multi-agent framework that leverages OpenAI and Google Gemini for citation-backed insights.

A modular, self-contained file format for executable AI prompts, logic, and data.

A modern, local-first AI chat interface built with Tauri, React, and Rust. Secure, private, and supports multiple LLM providers. 🚀

Fellow is a command-line interface (CLI) tool that acts as an autonomous software engineering assistant. It uses the OpenAI API to perform various structured tasks by reasoning step-by-step, executing commands, and maintaining a log of its activities.

Flutter application for AI Chatbot, AI Image Generation & Language Translation using AppWrite with OpenAI & Lexica search Api.

A tool to send requests to OpenAI in the form of natural language, get responses, interact, save prompts, use custom data and more

A simple AI source code that includes chat, reasoning and image features using public APIs like xAI, OpenAI, HuggingFace and Flux.

Accessing ChatGPT from the CLI (Command Line Interface)

A comprehensive web application designed to interact with a protein database. It includes functionalities for creating, reading, updating, and deleting protein data, as well as advanced features like an AI chatbot for SQL query generation and visualizations using Three.js.

Create a RAG AI chatbot with knowledge store from any website

An AI-powered Mattermost DeepSeek chatbot that utilizes the DeepSeek API to provide helpful, contextual responses to user messages, extract text from links, and describe or generate images. With Docker support!

A proof of concept framework for safely integrating generative AI and large language models into physical systems

We developed a SwiftUI-based iOS app 🚀 that serves as a hands-on demonstration for integrating the ChatGPT API 💬 into a chatbot-like 🤖 conversation experience. This interactive app will allow users to have engaging and dynamic text-based conversations with a virtual assistant powered by OpenAI's ChatGPT model.