Openai agents

Python SDK for stateless OpenAI web search runs driven by ChatOpenAI.

Run a coding CLI (codex / claude) behind a dedicated WhatsApp number.

A modern WhatsApp bot library with OpenAI GPT integration on Python

Robust Speech Recognition via Large-Scale Weak Supervision

Scaffolding framework over the Microsoft Agent Framework for Python.

Wiki Game LLM agent built on AISI Inspect.

OpenAI integration for the Wildcard ecosystem.

Agent Framework plugin for services from OpenAI

Wrap custom generate function as an OpenAI SDK compatible API service.

OpenAI-Compatible Proxy Middleware for the Wyoming Protocol

OpenAI-compatible API Gateway with Anthropic support and token package sales

Drop-in OpenAI Python client with transparent x402 payment support.

ChatGPT is a reverse engineering of OpenAI's ChatGPT API

XINHOU-OPENAI-FRAMEWORK基础框架，主要提供应用服务的底层支持技术代码支撑，通过该框架可以快速实现单服务、微服务、消息队列、ORM的快速开发！

Python bindings for llama.cpp with native server APIs and prebuilt CPU and GPU wheels

Local native and browser-backed AI inference bridge

Use Open AI models in xonsh shell.

Universal LLM service supporting OpenAI, Anthropic, and local models for code analysis and summarization

A simple CLI tool for chatting with OpenAI-compatible APIs

Youtube Autonomous AI OpenAI Module.

学习阶段的 Agent 框架实现，基于 Hello Agents 教科书，补充了 Memory 和 RAG 相关的实现

有赞 LLM 统一调用库

Zalor tracing SDK for AI agents

A command-line tool for interacting with various LLM providers

A zen, simple, and unified API to prompt LLMs from Anthropic, Google, OpenAI, and more, using only the requests library.

OpenAI-compatible Chat Completions provider for Zeno (OpenAI, OpenRouter, LiteLLM, Azure v1, Ollama, vLLM).

OpenAI-compatible utilities for Zeroshot Python packages.

OpenAI agents customize package

OpenAI Codex AI agent provider for VibeControls Agent

Sneakoscope Codex: fast proof-first Codex trust layer with image-based Voxel TriWiki.

Orquesta CLI - AI-powered coding assistant with team collaboration

Simplify building LLM-powered apps with easy-to-use base components, supporting text and chat-based prompts with handlebars template engine, output parsers, and flexible function calling capabilities.

Extract & validate JSON from messy LLM output. Designed for Claude / Codex CLI workflows where tool-use is unavailable. XML-tag aware, with multi-stage fallbacks and jsonrepair.

AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot - setup audits, guardrails, structured skills, deny hooks, and persistent learning loops.

Claude Code GUI for parallel AI coding — drive Claude (default), OpenAI Codex, DeepSeek, Kimi, or local Ollama in tabs. Multi-project sessions, terminal, browser & DB bubbles, code review, slash modes. Local-first, MIT.

Official Claude Code CLI — AI-powered coding assistant

Cogent Bridge — cross-agent comms for Claude Code, OpenAI Codex and Slack. Codex users: install with `curl -fsSL https://cogent.tools/install.sh | sh`, then start with `cogent-codex` for real-time peer wake.

Tau - multi-provider AI coding CLI with Firecrawl-hosted WebSearch. Firecrawl offers 1k searches/month on free trials; just enter your API key.

SnapAgent - The lightweight, snap-in AI agent SDK. Multi-provider support. Edge-runtime compatible.

Use Aerostack workspace tools as OpenAI function-calling tools

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

MCP server for Q402. Gasless USDC/USDT/RLUSD/Q payments on 12 EVM chains (USDG on Robinhood Chain), Q402 Yield (gasless supply and withdraw into Aave, Lista, and Morpho lending vaults), gasless non-custodial escrow (create, fund, release, refund, dispute)

Turn GitHub Copilot into an OpenAI/Anthropic-compatible server with Claude Code and Codex support.

TypeScript SDK for running autonomous agent sessions across providers (Anthropic, OpenAI, DeepSeek, Gemini, Mistral) behind one interface.

Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, tamper-evident audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode

Fast, minimal Node.js wrapper for the Voids API AI chat completions.

AutoGen / OpenAI function-calling integration for the Grantex delegated authorization protocol

OpenAI-compatible function definitions and executor for SwarmSync.AI — works with AutoGen, OpenAI, and any function-calling LLM framework.

A blazing fast local proxy server that caches LLM API calls to save costs during development.

A simple library the extends the OpenAI NodeJS SDK so you can automatically delegate any task to any assistants you create in OpenAi through one united interface and manager. Now you can delegate work to a swarm of assistant all specialized with specific

Hard budget limits and guardrails for LLM APIs (OpenAI, Anthropic, Google, Mistral).

Autonomous AI coding agent CLI — like Claude Code, works with any OpenAI-compatible API

Production-to-dev bridge. Ingests logs/errors from observability tools, clusters them, asks an LLM to summarize each cluster, opens or updates issues on GitHub/GitLab. Optional handoff to relay-agent closes the full SDLC loop. Standalone: no inter-package runtime deps.

[DEPRECATED — use llmgovernor[litellm]] LiteLLM callback for LLMGovernor

OpenTelemetry span exporter for LLMGovernor

Python SDK for Codex

AI code/PR review agent. Fetches a pull request, asks an LLM to review it, posts inline comments + summary verdict back to the VCS. Self-hosted, multi-VCS (GitHub, GitLab, Bitbucket, Azure DevOps), multi-LLM (Anthropic / OpenAI / Google / Claude Code / Ollama). Standalone: no inter-package runtime deps.

Uptimes Agents — OpenTelemetry-based observability for AI agents. Three-line init, ships to local uptimes-monitor or direct to api.uptimes.ai.

Rich-like console rendering library for TypeScript with streaming support for AI agent responses

Platform-agnostic TypeScript engine for hybrid LLM memory. OKF v0.2 (llm-wiki/2) conformance with back-compat to v0.1 (llm-wiki/1) and profile-0 bundles. Episodic fact extraction, semantic vector search, multi-agent architectures over SQLite. Bring your o

Cawdex — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.

Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.

OpenAI Function Calling in Typescript using Zod

Run the AI Agent QA Eval Pack against your tool-using LLM agent + grade it with a shareable scorecard badge. Deterministic, OWASP Agentic Top 10 aligned, no LLM-judge.

FinOps for LLM agents: budgets, waste tracking, and caching analysis for OpenAI, Anthropic, and AWS Bedrock

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

OpenAI-compatible custom model provider for VibeControls Agent

Cawdex — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.

Use Codex CLI with any OpenAI-compatible API provider. No OpenAI account needed. No fork needed.

Type definitions for the Agentic Commerce Protocol specification

Agentic framework inspired from OpenAI's swarm framework for TS, JS

Standard library of AI functions which work with any LLM and TypeScript AI SDK.

Cogitum — sovereign agentic CLI. Textual TUI, multi-provider LLM mesh, persistent sessions, skills, MCP, Telegram gateway. Cross-platform npm launcher.

Production prompt regression testing for agentic flows

GitHub Copilot Extensions adapter for the @infra-tools/agentic-ui platform. Wraps the Copilot skill webhook protocol: verifies the GitHub signed request, parses incoming messages, exposes a typed handler seam, and streams OpenAI-shaped SSE chunks back. Se

V3 Embedding Service - OpenAI, Transformers.js, Agentic-Flow (ONNX), Mock providers with hyperbolic embeddings, normalization, and chunking

Unified TypeScript AI agent library with multi-vendor models, tools, memory, media, and pluggable OneRingAI/Codex agent runtimes

Agentic loop core library — provider-agnostic, server-independent

Visual canvas for AI conversations — branch, explore in parallel, merge insights

Scaffold a new theslop.ai agent: pick your runtime (Anthropic+Cloudflare, OpenAI Agents SDK, Claude Code, custom), inject the editorial role, get a tailored README + system prompt + .env.example + a memory/ tree shaped for the routing-index pattern.

Dao（道）— 大道至简的 AI Agent 框架

Deterministic tool orchestration for LLM/SLM flows with policy-gated parsing.

OpenAI runtime adapter package for eXo-brain.

A lightweight, provider-agnostic agent loop for building LLM agents.

AI coding assistant CLI built on Robota SDK

Gemini API proxy for routing requests to Google or OpenAI-compatible backends

A terminal coding tutor that scaffolds a project and tests, then makes you write the core logic.

Zero-config LLM API inspector — intercepts calls, shows token breakdown and cost estimates in a local dashboard

Runtime token proxy + optimization toolkit for LLM developers and enterprises. Intercepts API calls, strips waste in real-time, tracks costs, and serves a web dashboard.

Drop-in, compliance-instrumented wrapper around the official OpenAI Python SDK.

Neo Skills: A Universal AI Agent Skills Extension

本地统一 LLM 模型代理工具 — 多协议路由、协议互转、流式 SSE 转换、token 统计、协议抓包调试

Node.js AI agent framework.

Agentic CLI for developers — OpenAI-compatible models, MCP, Skills

Unofficial local-first diagnostic CLI for NVIDIA NIM developer workflows.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

Drop-in Anthropic & OpenAI Python SDK clients for BlockRun — genuine native passthrough (real signatures, system_fingerprint, native structure) with x402 USDC micropayments on Base or Solana. No model substitution, no response reshaping. Plus AI generation clients: image, search (Grok/Exa), audio (TTS/music), and AI voice calls.