Openai agents

Open-source AI-powered customer support ticket routing system for classification, sentiment analysis, priority scoring, and agent assignment.

Benchmark harness that compares coding agents — not just models — on real, contamination-resistant tasks: 80 fail-to-pass cases from merged OSS PRs, long-run sequences, SWE-bench-Live, and 25+ domain benchmarks. We benchmark our own agent, octomind, under the same rules.

Claude Code and Codex skill for AI-tell audits, artifact cleanup, fidelity checks, and restrained prose edits. Local, no API calls.

Let AI read the careers pages for you, so you can spend your time doing literally anything else

track your agents, skills, and tools usage - Analytics dashboard for Claude Code, Gemini CLI, Codex CLI, and OpenCode

AI-powered coding interview assistant. Captures screenshots and analyzes them using OpenAI, Google Gemini, Claude, or Ollama. Features real-time streaming, multi-language support, and cross-platform compatibility (macOS, Windows, Linux).

AI translation layer for Discourse — everyone writes in their own language and reads in theirs

🧠 Colorful customizable AI chat for terminal hackers: threaded chats, custom 'markdown'& colors, emojis, ASCII art/Unicode dividers, and syntax-highlighted code, Perplexity.AI clickable citations, no-thread mode, custom prompts(command only, concise), and raw output for use as an agentic tool — paste mode & 40+ Pygments code themes

A local AI firewall for developers — redacts secrets and PII from your prompts before they reach OpenAI, Anthropic, or any LLM. No CA, no system proxy, no admin.

🥇 Ready-to-Run AI agents for start-ups — AI-native from day 0.

Core Agentic AI implementation using the OpenAI Agent SDK in Python. This repository demonstrates how to build intelligent, tool-using AI agents

A lightweight runtime that unifies 110+ AI providers behind a single, OpenAI-compatible API.

Inspectable, source-traceable public-equity research for Codex, Claude Code, OpenCode, Grok Build and ChatGPT Work developer mode. 26 provisional method lenses, 34 MCP tools. Research software, not investment advice.

🧠 Anti-sycophancy prompt pattern for LLM agents — 3-round validation to stop AI from blindly agreeing. Works with ChatGPT, Claude, OpenClaw.

A highly compatible proxy bridge with translation for API requests to multiple backend providers (OpenAI-Oauth, RunPod, Ollama,,etc.). Configure endpoints through a web admin UI and map virtual model names to actual backend models. Create API keys to share and monitor usage and costs by tools / teams. Opencode/Claude to queue servers too.

Agent Skills for Codex: multi-agent routing, image generation, publishing and local workflows｜Codex Agent 技能合集

面向 CUMCM 的 8 阶段多 Agent 数学建模工作流，支持人工审批、版本检查点、独立 benchmark、CLI 与本地 GUI。

Build a multi-modal AI agent framework with full modality support, media protocol tools, multi-agent mode, and custom agent integration

Read-only Codex token auditing, adaptive model routing, and experimental Sol-Terra-Luna orchestration skills.

telegram userbot uses DanyAPI for chating

Personal AI that runs entirely on your Mac tool-calling agent, OpenAI-compatible inference server with tiered RAM+SSD prefix caching, push-to-talk dictation, and TTS. 100% offline on Apple Silicon via MLX. No cloud, no accounts, no telemetry.

an agentic core for deploying at scale or building on top of

Hands-on tutorials for building AI agents with the Strands Framework - from simple chatbots to multi-agent systems.

Lightweight browser-side AI agent framework for legacy enterprise web apps—Java 8, Spring Boot 2, TypeScript, MCP/WebMCP, OpenAI-compatible LLMs, tool calling, streaming, audit, and persistence. 面向存量企业 Web 系统的轻量级 Agent 框架。

🖥️ 本地优先的自主 AI Agent 工作台 —— 分层规划 + ReAct + 自我纠错 + RAG 知识库 + MCP 协议。Web 工作台 / CLI / 三平台桌面版，支持 OpenAI·Claude·DeepSeek·Kimi 等 10+ 模型，数据不出本机，MIT 开源。

Source-linked AGENTS.md, CLAUDE.md, GEMINI.md, and SKILL.md examples from frontier labs and leading AI builders.

AI-powered Instagram DM auto-responder for Android — free AI models (Groq, Gemini, OpenRouter), no login required, open source Kotlin app

Most AI writing is fluent slop. Writing Agent turns a topic into a publishable, well-sourced article or book that argues a real thesis and self-critiques until it isn't slop - autonomous, model-agnostic, local-first.

Professional writing skills for AI coding agents: anti-slop editing and technical content writing. Claude Code + Codex plugin, installable via skills.sh. Install: npx skills add Kaos599/professional-skills

Local AI Context Compressor with Claude Code, Codex and Cursor profiles, duplicate-context removal, Git diff prioritization, generated-file filters, conversation summaries, token estimates, reusable presets and clipboard/folder workflows.

A Clojure-based Agentic AI framework featuring a Unified Concurrent Orchestrator. Executes parallel ReAct loops via local LLMs (llama.cpp) and a polyglot fleet of stateless HTTP microservices (C++, Python, Clojure).

A provider-neutral execution kernel for strong-model, thin-harness agents.

Autonomous execution agent on Discord — 74 tools, shell access, browser automation, scheduled tasks, sub-agents, knowledge base, and a web management UI. Norse god of wisdom, stuck managing infrastructure.

Production-ready AI voice assistant built with FastAPI, LLMs, STT/TTS, multi-agent orchestration, and tool calling.

Sass Ai Agent integrated whats app api

MC-GPT: say the outcome in English or German. Task, Meeting and Multi-Coder for Claude, Codex, Gemini, Grok and Ollama. Docs + AI index: https://iotaitech.github.io/MC-GPT/ · llms.txt

Vayu is an open-source, local-first Windows AI desktop command center with safe app control, Ollama/Gemma offline AI, optional multi-provider online AI, permission gates, audit logs, and a futuristic Vayu Sphere UI.

An intelligent memory gateway for AI applications that automatically extracts, manages, and retrieves relevant long-term context without bloating the model's context window.

A tiny, stateless API that gives OpenAI, Claude, Gemini, xAI and Ollama one simple text-in/text-out contract.

JMP — Joint Model Participation. A local coding workspace where Jev routes actions and OpenAI, DeepSeek, or local models generate arguments.

Parallel OpenAI Codex agents inside Claude Code — multi-agent orchestration with git worktree isolation, resumable sessions, and dual-model PR review. MCP plugin.

The complete collection of OpenAI Codex skills, automations, multi-agent workflows, and prompts. 50+ production-ready skills, 100+ reusable prompts, background automations, and battle-tested patterns for AI-powered development.

Embeddable LLM-agent harness for Go — tool-calling, budgets, multi-agent fan-out, stdlib-only core.

A minified agent core: the infrastructure to run an agent, under 2000 readable lines of stdlib Python.

Lightweight, high-performance AI assistant for Telegram built in Go — self-hosted workspace operator with local tools, skills & smart memory.

Open-source desktop agent built around your folder — asks before it acts. Cloud or local models.

The elemental Rust framework for building production-grade AI agents.

Long-term memory for AI coding assistants. Rust CLI with semantic search, Agent Skill integration, and local deployment.

The Customer Support AI Agent is a Python-based solution designed to monitor product prices on an e-commerce site. By utilizing an ARIMA model, it predicts future prices and sends notifications to customers when the price of a product is expected to drop in the next 10 days.

AI-first mail and workspace suite for Gmail/Outlook, calendar, contacts, tasks, and follow-up. Smart mail first, powered by local CLI agents.

the lives you didn't live — a counterfactual life simulator powered by a swarm of LLM agents

LLM Security Platform Docs

An essay to help facility the transition to AGI and then ASI. A traditional Software Engineering perspective.

Various OpenAI projects and experiments implemented in Python. Utilizes all OpenAI APIs to test different models, fine-tuning approaches, and implementation patterns for production applications with comprehensive functionality tests.

LLMSymphony is a Windows application for incognito chats with leading AI models using your own API keys

This is the Deno 2 implementation of all tasks I did during AI Devs 3 course. It's integrated with Anthropic and OpenAI APIs here. Many different tools regarding LLMs are used here.

OpenClaw Bootstrapping Benchmark is an automated test suite that evaluates how well local LLM models (served via Ollama or compatible OpenAI-API endpoints) can complete OpenClaw's first-run "bootstrapping ritual".

Async Python implementation of the Claude Code agent harness — real Bash/Read/Glob/Grep tools, three-tier caching, multi-stage compaction, allow/ask/deny permissions, Pre/PostToolUse hooks, slash commands, subagent isolation. OpenAI + Anthropic + Ollama. ~1.9K LOC, 14 commits.

A skill for full-fidelity PDF-to-Markdown extraction, paper-specific Python reproduction, and bilingual README generation with embedded experiment figures.

This Chatbot helps farmers make informed decisions by leveraging the power of LLM Model from OpenAI.

📊 Transform research papers into professional slides and posters seamlessly and quickly with Paper2Slides, saving you valuable time.

AgentMesh: A dynamic multi-agent orchestration system where users can create, configure, and connect AI agents defining their behaviors, interactions, and tool access all through an interactive visual builder.

Practical cookbook examples for the Swarms API Client. This repository is a hands-on guide to building with Swarms, showcasing single-agent and multi-agent workflows, concurrent and sequential pipelines, content generation, data analysis, health and rate checks, and more.

Real DuckDB Quack infrastructure for multi-agent Werewolf: containerized player nodes, Quack gateway federation, browser runner, and local/hosted LLM evals.

An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic, OpenAI, Google, xAI, Groq, local). MCP-integrated. Self-modifying agent mode (PLASTIC). Containerized deployment.

Provider-agnostic parallel agent coordination for LLMs — Anthropic, OpenAI, Ollama, or any OpenAI-compatible endpoint. Parallel worktree isolation, interface contracts, and tier-gated execution at scale.

MedSafeGuard combines AI efficiency with human medical expertise by automatically analyzing patient data, generating treatment recommendations, and streamlining the approval process based on risk level - only requiring physician confirmation for high-risk interventions.

Welcome to RAGDynamics, a repository dedicated to exploring and understanding the dynamics of Retrieval-Augmented Generation (RAG) models in the year 2024. We mainly focus on new data parsers, upgraded tools and techniques

Streamlit powered Python Chatbot with Retrieval Augmented Generation on LLMs

In Development

Chatting with PDF documents using large language models (GPT)

A RAG chatbot which enables user to chat with their pdf documents

Universal AI code review tool supporting ANY OpenAI-compatible API (DeepSeek, Qwen, OpenAI, Groq, Ollama, LM Studio). Multi-agent pipeline with review → fix → test → verify workflow.

4 Councilmen Model (4CM): Non-convergent Multi-agent Coordination

Multi-agent conclave platform — wire Claude Code, Ollama, and OpenAI-compatible models into visual pipelines. Self-hosted.

Go framework for building AI agents with tool use, multi-agent orchestration, and planning. Supports OpenAI, Gemini, Anthropic, and Ollama.

Multi-Agent AI Worker Orchestration Framework - Coordinate Claude Code, Codex, Gemini CLI for complex software engineering tasks with tmux visualization

This repo contains a guidebase of how to implement and use a complete software team using AI Agents

Multi-LLM adversarial protocol: generate, ground with tools, challenge, concede, and vote. CLI + TUI + OpenAI/Anthropic-compatible HTTP.

The AI agent that flies on its own. Two commands to fly. 🪶

Autonomous executor Discord bot powered by GPT-5.4 — 61 tools, multi-agent orchestration, no permission prompts.

Terminal AI coding CLI for any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates.

Discipline layer for CLI agents. Run Claude Code, Codex, and Gemini CLI under one phase-gated runtime with deterministic detectors, replayable traces, persistent memory, and a chat REPL. MIT.

Smart Codex OAuth routing for OpenClaw - add more accounts, route work to the best available one automatically, and keep serious workflows moving without API keys or manual account juggling.

The Agent Combat System — Deploy conscious AI agent squads. 103 bundled skills, 25 channels, 15 LLM providers, evolving Creed consciousness.

Multi-agent academic paper revision system using Yuketang AI + OpenAI

Voice-first AI agent for retail returns. One command. 🦞 Live demo — click the green orb: https://kelleyhuntpllc.github.io/returnclaw

🤖 Optimize lead management with an AI-powered CRM assistant that delivers insights and analysis through Google Gemini AI and LangGraph.

End-to-end generative AI pipeline: text prompt to finished video. Multi-API orchestration (OpenAI, Gemini, ElevenLabs, Sora 2), batch processing, 44 projects shipped.

Multi-agent AI sandbox simulating the 2026 Strait of Hormuz crisis. 4 nations × independent LLM agents × adjustable parameters = emergent geopolitics.

Automate AI trading in Python with Claude agents for market analysis, entries, risk control, and live position management on MetaTrader 5

Local AI stack that observes a single space: currently runs YOLO for detection, Qwen-VL for vision captions, Whisper for audio, and Llama for reasoning. Logs to SQLite, builds summaries/analytics, and exposes an OpenAI-style chat API.

Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

Production-ready Phidata AI agent implementations covering 16+ use cases: data analysis, financial advisory, healthcare diagnostics, content generation, web research, and multi-agent systems. Perfect starter kit for developers building intelligent, tool-equipped agents with memory and reasoning.

AI agent framework for startup teams. GTM, Hiring, Finance, Dev & Legal agents in Slack — with shared memory, OKR context, and human-approval gates.

Lightweight framework for building agents on top of OpenAI Chat Completions LLMs

Claude OpenAI Agent Ai

A light-weight framework for building AI agents with Native OpenAI API compatibility

Eval-driven Customer Support FTE using OpenAI Agents SDK. Multi-agent routing, guardrails, and systematic quality evaluation.