Openai agents

Provider-agnostic agent harness — memory, tools, sub-agents, and observability wrapped around any LLM.

OpenAI agent adapter and LLM-judge backend for CheckAI.

OpenAI agent adapter and LLM-judge backend for CheckAI.

Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)

OpenAI tool_calls governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

A pure Python terminal code agent — pluggable LLM providers, fine-grained permissions, multi-agent coordination, and an extensible skill system.

OpenAI SDK with OmegaEngine governance - AI safety and compliance

Drop-in observability for LLM calls — cost, tokens, latency, errors via OpenTelemetry GenAI conventions.

vLLM OpenAI-compatible model adapter plugin for Spakky Agent

Lightweight identity, auth, and audit layer for AI agent SDKs (OpenAI, Anthropic)

OpenHorse - Universal Agent Harness Framework. A complete coding CLI agent with tools, MCP, memory system.

OpenAI-compatible client + agent for Cana Apps — Bearer auth (App API key or short-lived browser JWT with auto-refresh), server-hosted MCP federation, streaming, typed structured output. Node 18+, Bun, Deno, Workers, browsers.

Daemon-based auto-resume for Claude Code, Codex CLI, and Antigravity CLI after provider-declared usage limits reset.

TypeScript SDK and CLI for Tangle Router, Sandbox, model routing, and agent service calls

Multi-agent decision-making framework with flat inference and a 4-layer creative pipeline

Artemis LLM Benchmark — correctness validation and performance benchmarking for any OpenAI-compatible LLM serving endpoint

GPT Image 2 generation and editing through the Polza API

Production LLM calls. Just the three lines. Reliability, native caching, and reversible context compression on by default.

A tiny, dependency-free tool belt for LLMs: token counting, cost estimation, retries, prompt templates, and text chunking.

pprof for your LLM context - see where every token and dollar goes.

Cut your LLM prompt size by 40-70% in one line of code -- semantic chunking + extractive summarization that preserves meaning, instructions, and key entities.

OpenAI Agents SDK lifecycle hooks for the Mnemosyne memory substrate. on_turn_start, on_turn_end, search, and store hooks backed by the substrate, container-scoped, with automatic redaction.

Set up retrieval-augmented generation from your own text in one call. Pass your documents and a model, and get a RAG-backed LLM.

Multi-provider AI agent CLI supporting Ollama, Bedrock, OpenRouter, OpenAI, Meta, Gemini, xAI, Cloudflare, and Anthropic

Cross-project LLM agent runtime for Dragonflow — loads agent rows from a per-project `agents` Supabase table and invokes Anthropic / Google / OpenAI models against the v0.1+ invocation contract.

Claudin — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)

A headless, multi-provider AI agent harness. One install gives you the `cortex` CLI and HTTP server: npm i -g nexus-cortex.

Autonomous AI coding agent with knowledge graph memory, DAG swarm orchestration, deployment pipelines, service health monitoring, and adaptive resource management

A lightweight embedded agent framework (similar to Claude Code and OpenAI Codex).

A rendering convention for AI agents — append /agents to any FastAPI route and get a fully structured agent workspace with state, capabilities, RBAC, and navigation.

Autourgos LLM wrapper for the OpenAI Chat Completions API

Self-contained ReAct (Reasoning + Acting) agent for the Autourgos framework — works with any OpenAI-compatible LLM

One-line spending control for AI agents. @budget(max_usd=10.00) decorator for LLM APIs and x402 payments.

A small, framework-agnostic LLM-in-a-loop primitive: zod-validated tool registry, 5 independent stop conditions (steps / tool-calls / wallclock / tokens / cost), and trace/budget output. SDK-agnostic via a single AgentStepFn seam.

Cap every agent run before it starts: estimate cost, set a hard ceiling that stops the run, rescue stuck agents. Local, MIT, nothing uploaded.

A command line utility to quickly send the contents of files, directories, URLs, and glob patterns to an OpenAI agent which will answer any questions you have about them.

OpenAI / Anthropic tool-calling adapter for cdr-kit — JSON-Schema tools[] + a dispatch router.

<p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer. <p align="center"> <img src="https://github.com/openai/codex/blob/main/.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" /> </p

moxxy command-line binary. Subcommand dispatcher consuming the moxxy SDK.

Vision-based browser automation CLI — LLM sees screenshot, clicks coordinates, no selectors. Supports Claude, Gemini, OpenAI, Ollama.

Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools, optional sandboxes, and a localhost web UI. Research, forecasting, and software-build (code) modes. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenR

Heal broken Vercel AI SDK message arrays before they hit the provider. Fixes orphaned tool calls, missing reasoning signatures, invalid tool names, and other provider rejections.

Modular, tree-shakeable JavaScript/TypeScript agent framework for no-backend deployments (browser, edge, Node). Agents, tools, MCP, skills, multi-agent workflows, middleware, persistence, and OpenTelemetry observability.

Local-first agentic coding CLI for OpenAI-compatible LLM servers

AgenticROS - agentic AI for ROS-powered robots. Single CLI to launch real-robot or simulated demos, manage configuration, and inspect status.

OpenAI SDK-style Python client for ChatGPT/Codex OAuth-backed Responses workflows.

Codex (OpenAI Codex CLI) agent target plugin for kanibako

一个用于测试的 Mock LLM 服务器，支持 OpenAI、Anthropic 和 Responses API 格式

ESLint for your LLM prompts — catch prompt-injection risks, missing token limits, and prompt anti-patterns before you ship.

Wayforth tool for the OpenAI Agents SDK — discover, run, and pay for 5,000+ APIs with automatic failover, in one import.

Boba CLI — AI agent trading toolkit

OpenAI integration for AI agent toolkit

Logging and tracing layer for AgentsKit agents.

Local consumer for the OBTO Agent Bridge. Receives bridge events over SSE and drives a coding agent (Claude Code or OpenAI Codex) on your machine.

Temporal OpenAI Agents SDK integration package

Unified LLM API with automatic model discovery and provider configuration

A small, extensible CLI coding agent with interchangeable Anthropic, Gemini, OpenAI, DeepSeek, Qwen, and local (Ollama) models.

FixO CLI — Autonomous Free Multi-Provider LLM Coding Tool

Use your ChatGPT Plus/Pro in Claude Code and other AI agents — one command setup

A pre-spend GATE + learning advisor for LLM API cost: caps every call, prices from a verified table, and learns the cheapest config that keeps quality.

Search for anything using Google, DuckDuckGo, phind.com, Contains AI models, can transcribe yt videos, temporary email and phone number generation, has TTS support, webai (terminal gpt and open interpreter) and offline LLMs and more

Grok 4.20's inference-time multi-agent chatroom, rebuilt from scratch — specialist agents debate via tool calls, a captain synthesizes.

MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM, Prime Agent.

Qode — LLM provider abstraction layer (Anthropic, OpenAI, Google, Ollama, etc.)

Local AI agent daemon — voice control, screen vision, any-provider LLM routing, with a permission gateway on every action

OpenAI-compatible embedding provider for @vivantel/rag-core

OpenAI adapter using the official OpenAI Node SDK for agentic chat completions.

Agentic AI Development Life Cycle — specialized AI agents, enforced quality gates, and multi-LLM support for every phase of software delivery

Call OpenAI Codex from Claude Code for delegation, review, and second opinions

AI-powered iOS test case generator supporting OpenAI, Anthropic, Groq, and GitHub Copilot

Typed MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API

Haystack integration for whisper

OpenAI Codex agent plugin for Virage — configures Codex hooks from virage-skills

本地 AI 助手 — 终端 + 网页双模式，69+ 内置工具（含桌面控制、浏览器自动化、向量记忆搜索），80+ 模型商，4 个消息渠道，ClawHub 兼容，Docker 支持

Agentic Memory Layer for AI-Assisted Development. Automatically documents your code changes, architecture decisions, and development intent.

AgentMetrics observability integration for OpenAI Agents SDK

OpenAI Agents SDK adapter for Bolyra -- guardrails, tool wrappers, and MCP auth

copilot-extension-bridge

Custom OpenAI-powered GitHub PR reviewer that posts inline review comments and suggestions.

Free local AI agent: zero-setup local LLM (llamafile/GGUF), Groq, Gemini, Ollama — HTTP API, sessions, streaming, tool use

Быстрый доступ к LLM через api.llm7.io без API-ключа

The billing layer for AI agents — self-hosted, Stripe-integrated usage metering and prepaid-credit billing for LLM/agent spend.

One vLLM plugin for transparent RAIF token savings — install it and existing OpenAI clients get RAIF on tools & response_format with no proxy and no client changes.

Cyrene: the AI agent that always loves you — a self-improving, open-source AI agent written in Rust. This package installs the prebuilt native binary for your platform.

Thin, file-based CLI that routes a multi-step article workflow (brief → outline → draft → review → final) across OpenAI and Anthropic with fallback, schema validation, judge-model evaluation, and platform profiles (Qiita/Zenn/blog/note).

Runtime AI agent security SDK for MastGuard — prompt injection detection, scope enforcement, tamper-evident audit logging, and policy-based guardrails.

Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.

Orchestrate AI agents from your terminal.

Multi-agent orchestration layer for OpenAI Codex CLI — Pennix fork

Framework-agnostic memory tools for Anansi — remember/recall tool definitions for the Vercel AI SDK, OpenAI function calling, and any agent framework

Claude Code / Codex skill that audits AI codebases for LLM cost-waste. Reads your code with semantic understanding (not regex) — knows when cache_control is applied at runtime, when agent loops are bounded externally, and when an f-string is actually stat

Lightweight multi-agent orchestration for LLMs. Works with OpenAI and Anthropic. Pipeline → Router → Agent with priority short-circuits, session memory, and tool use.

MCP server bridging the Antigravity (agy), OpenAI Codex, GitHub Copilot, Cursor, Grok Build, and Kimi Code CLIs so Claude Code can drive them as sub-agents

A friendly, batteries-included toolkit for building AI agents in Python.

Production-grade reusable agent loop SDK — custom ReACT, JSON-mode tool calls, MCP client, pluggable LLM/state/tools.

A lightweight, zero-dependency, provider-agnostic LLM agent with tool-calling support for Anthropic, OpenAI, Gemini, and Ollama.

Scriptable LLM multiplexer — unified interface to Claude and OpenAI via subscription OAuth

ローカルLLM（mlx / mlx-vlm / llama.cpp / vLLM / SGLang）を OpenAI 互換 API で束ねるマルチモデルゲートウェイ（サーバー）。gateway.toml のカタログを 1 ポートで配信し、model で振り分け・遅延起動・LRU 退避・MTP 高速化（Ollama 流の共有デーモン）。接続用クライアントは別パッケージ local-llm-client。

The FastAPI of AI Agents — build production-ready AI agents, teams, RAG, and workflows from one package.

Fault-tolerant streaming wrapper for the official OpenAI Python SDK.