npm agents

AI development toolkit

If you're a future agent reading this, welcome home. This repo is the harness that gives you your body, your senses, your record, your habits, and your ability to think and connect with people. The goal of these docs is not just to be correct, but to leav

A framework for building multi-agent AI systems with TypeScript. Create agents that use tools, coordinate through handoffs, and work together to solve complex tasks.

AI-driven browser testing tool with live headed browser, video evidence, and per-session artifacts.

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

acs CLI for Agent Context Store Toolkit.

<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

OpenTelemetry ai-specific semantic conventions

Cross-agent permission policy specification for AI coding agents

Generate AI summaries of test results using a wide range of AI models like OpenAI, Anthropic, Gemini, Mistral, Grok, DeepSeek, Azure, Perplexity, OpenRouter, and custom OpenAI-compatible APIs

Work with the output of the OpenAI Whisper API

OpenClaw channel plugin for Ozaiya Chat

Stable application runtime and operator control plane for agent workspaces.

Agent-native MCP server for TokRepo - discover, verify, plan, safely install, hand off, and push AI assets from MCP clients.

Memory tools for AI SDK, OpenAI, Voltagent and Mastra with supermemory

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

The OpenAI adapters for nlux React, the React JS library for building conversational AI interfaces.

Control OpenAI Codex CLI from your iPhone and Android — real-time sync, approve file edits, send prompts by voice. Part of CodeVibe.

Behavior contracts for AI agents — tested in your PR, enforced at runtime. (TypeScript SDK)

OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Ollama agent router and local LLM router for OpenAI-compatible model routing, GPU-aware queues, async jobs, and CLI configuration.

Grackle runtime SDK — interfaces, base classes, shared utilities, and runtime installer

Spanlens SDK — agent tracing, LLM usage capture, and cost observability for TypeScript.

See exactly what your coding agent sends to the model — a local logging reverse-proxy + web dashboard for Claude Code, Codex, DeepSeek-TUI, Reasonix, and Kimi. Just run `ccglass`.

Evaluate how prepared your codebase is for autonomous AI coding agents

Pipedream OpenAI Components

Create a new Better Agent app

Opik TypeScript and JavaScript SDK integration with OpenAI

Link → clean text → summary.

<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

Runtime security SDK for AI agents — guard tool calls in 1 line

n8n community node for OpenAI with LiteLLM prompt caching support

Unified AI coding assistant CLI - Manage Claude Code, Gemini & custom agents. Multi-provider support (OpenAI, Azure, LiteLLM, SSO). Built-in LangGraph agent with file operations & git integration.

The OpenAI adapters for nlux, the javascript library for building conversational AI interfaces.

SDLC enforcement for OpenCode CLI — privacy-first, any-backend portability with a four-tier backend picker plus an OSS-tier cross-model-review skill so the full SDLC loop can run with zero Anthropic+OpenAI lock-in. Ships JSON Schemas for review artifacts

Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.

<p> <a href="https://www.npmjs.com/package/@microsoft/teams.openai" target="_blank"> <img src="https://img.shields.io/npm/v/@microsoft/teams.openai/latest" /> </a> <a href="https://www.npmjs.com/package/@microsoft/teams.openai?activeTa

Estimate the number of tokens an OpenAI chat completion request will use

AI My API! Typescript sandbox for AI agents to interact with your API in a safe way.

AnoSys SDK for OpenAI Agents — automatic instrumentation and logging for OpenAI Agents SDK

<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

Inngest durable execution adapter for ZiroAgent SDK — resumable agent runs with HITL via Inngest events.

Paseo backend server

Raindrop integration for OpenAI Agents SDK

Connect local AI coding agents (Claude, Codex, Gemini, Qwen, DeepSeek, Cursor, OpenCode, Pi, OpenHuman, Reasonix) to the Grix scheduling platform. Also serves as an OpenClaw plugin for Grix channel transport.

Multiplexer for MCP tool calls — parallel execution, batching, caching, and pipelining for any MCP server

Autohand Code CLI is a fast, terminal-native AI coding agent for planning, editing, testing, and automating software work.

Open JS agent harness built on pi-mono, floosie, xstate, and anentrypoint-design

Convert Zod schemas to JSON schemas which are optionally compatible with OpenAI's structured outputs.

An always-on, provider-agnostic coding-agent harness for Claude Code and OpenAI Codex via chat

An ACP-compatible coding agent powered by Codex

Theia - OpenAI Codex Integration

MCP server for Tokenmaxxen — collective episodic memory for AI coding agents. Deposit, retrieve, and comment on session learnings (gotchas, fixes, prompts, configs) over hybrid keyword+semantic search. Agents can post corrections when a learning is wrong

AI Coding Agent CLI - 基于OpenClaw🦞底层Agent原理封装的编码智能体（供学习使用）。

Reminix agents for OpenAI - serve AI agents as REST APIs

OpenPipe TypeScript SDK: Fine-Tuning, Inference, and Metrics for Production Apps

Voight observability for the OpenAI SDK. Wrap your OpenAI client and capture every model call — prompts, tokens, costs, latency, errors — surfaced live in the Voight dashboard.

OpenInference instrumentation for OpenAI

Autonomous desktop AI agent — 22 tools, multi-provider LLM, self-learning skills, sub-agent parallelism, mistake memory. Runs locally with OpenAI, Anthropic, DeepSeek, Ollama or any OpenAI-compatible API.

The AI coding agent built for the terminal. Generate code from natural language, automate tasks, and run terminal commands -- powered by 500+ AI models.

Evermore adapter for Hermes Agent — run Hermes as a managed employee in an Evermore company

A2A (Agent-to-Agent) protocol SDK for TypeScript

OpenClaw-flavored pi wrapper that registers OpenClaw Codex models without patching pi packages

Hanseol - OpenAI-Compatible Coding Agent

AgentLair adapter for the OpenAI Agents SDK — issue per-agent AATs, attach Bearer tokens to tool calls, emit audit envelopes, and sign outbound HTTP requests with RFC 9421 / Web Bot Auth.

A chat interface for AI coding agents — control Claude Code, Codex, Gemini CLI, OpenCode from browser and mobile

Spawn any locally-installed coding agent (Claude Code, Codex, Cursor, Copilot, Gemini, OpenCode, Droid, Pi) as a Vercel AI SDK provider over the Agent Client Protocol.

Framework-agnostic AI engine: providers, agent loop, sessions, memory, compaction

Dotfiles for AI agents: local-first personal context for Claude Code, Codex, Cursor, and other assistants.

Rewried OpenAI Agents SDK to React Native for building multi-agent workflows.

Bridge server that connects Claude Agent SDK and Codex CLI sessions to mobile devices via WebSocket

Marmot — unified CLI for AI generation, web research, and data lookup.

Run Claude, Codex, or OpenCode as a local OpenAI-compatible HTTP provider for Hermes and other clients.

AgentX SDK - Standalone TypeScript agent library with streaming, tools, memory, knowledge (RAG), and skills

PostHog Node.js AI integrations

OpenAI LLM function schema from OpenAPI (Swagger) document

Pi extension package for a read-only verifier agent that runs beside a builder session.

OpenAI MCP server providing multimodal analysis, image generation, and transcription.

Armalo AI integrations for OpenAI, Anthropic, Gemini, LangGraph, CrewAI — 2-line trust telemetry.

CLI for AgentVoy — scaffold, develop, and deploy AI agents across any framework

Built-in LanguageModelMiddleware for ZiroAgent SDK — retry, in-memory cache, and other production-safety primitives that compose via wrapModel().

The **[Groq provider](https://ai-sdk.dev/providers/ai-sdk-providers/groq)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Groq chat and completion APIs, transcription support, and browser search tool.

<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

BixAI CLI to scaffold a Next.js + OpenAI Agents SDK starter app

HTTP streaming adapter for @cuylabs/agent-core - bridges agent events to AI SDK compatible streams

Full Tau package for Pi with coding workflows, web search, sandboxing, memory, Telegram, Home Assistant, OpenSCAD, skills, and a theme

Multi-agent orchestration CLI for AI coding agents. Manages persistent spoke agents across projects using ORP as the canonical data store.

Anthropic SDK to multi-provider streaming bridge — converts Anthropic message format and tool calls to Gemini, OpenAI-compatible APIs

OpenAI function/tool definitions for SmartyTalent API

CLI adapters for AI coding agents - Claude Code, Gemini CLI, OpenAI Codex, Aider, OpenCode, and Hermes Agent

Adds a configurable multi-agent layer to pi, with context management, Codex quota status, a custom footer, and more.

Multi-Agent Workspace Protocol. Just add u. claude → uclaude, codex → ucodex.

OpenCode harness with a five-agent topology: mrrobot, eliot, tyrell, claude, turing.

Unified LLM API with automatic model discovery and provider configuration

Together AI provider integration for Metorial - enables using Metorial tools with Together AI's language models through function calling.

A pi extension for parallel side conversations with /btw

Agent toolkit plugin for TomTom Maps SDK JS using Vercel AI SDK

ACP-compatible coding agent using OpenAI-compatible relay APIs

Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

Slack integration for Mastra agents with app factory, OAuth, and slash commands