npm agents

An interactive coding agent and command line utility for coding tscircuit TSX circuits

OctoCode - AI-powered development tool by Farhan Dhrubo

SPS CLI — AI-driven development pipeline orchestrator

AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,003+ agentic skills.

Eden TypeScript runtime SDK — auto-instrumentation for OpenAI, Anthropic, Vercel AI, LangChain, Mastra, Bedrock, and Gemini with fire-and-forget telemetry to the Eden gateway.

Fast service-tier extension for pi-agent.

NexusAgentX distribution of the OpenAI Codex CLI.

Rulvar umbrella package: re-exports @rulvar/core, both first-class adapters, the file store, and the terminal progress renderer. Also installable through the unscoped alias package rulvar, which re-exports this one.

Provider-native web search for pi across Google Gemini, OpenAI, and Anthropic, plus Gemini URL Context

MongoDB-backed persistent memory provider for the Vercel AI SDK — Session, Semantic, Procedural, Episodic, and Scratchpad memory with Atlas Vector Search.

Veryfront first-party extension package for ext-llm-openai

Olympus dashboard for monitoring OpenClaw workspaces, agents, lineage, configuration, cron activity, and costs.

Free OpenAI API access with your ChatGPT account.

AgJSON core — the typed schema (AgInput / AgEvent / AgMessage), the Normalizer interface, and the normative reduce().

Agent-Nuvira: Multi-agent AI coding CLI — plan, write, review, test, and publish code with local models (Ollama) or cloud APIs (Groq, NVIDIA NIM, Google Gemini, OpenRouter)

GoNext CLI — the gonext terminal plus the local worker that runs agent / OCR / PDF / embedding jobs on your Mac (Ollama / MLX / OpenAI-compatible).

AI Coding Agent — CLI and TUI interface with CI automation support (ReAct loop + built-in tools + skill system)

9Router v2 — Monorepo (frontend + backend)

A context-first, model-agnostic coding agent with an auditable terminal workspace.

Synx Connector — the local CLI/daemon that bridges a coding agent (Claude Agent SDK or OpenAI Codex SDK) on your machine to a Synx workspace over an authenticated WebSocket control channel.

TypeScript SDK for the MiMoCode API

MCP server with an integrated ReAct mini-agent that autonomously uses tools. Includes AnySearch integration for web search and multi-model LLM communication via MCP sampling.

TypeScript SDK for connecting to Runloop-hosted remote agents using Axons

OpenAI-compatible API gateway for Grok CLI — with Admin panel, safe mode, and gctoac CLI

OpenAI-compatible language model adapter for Pilot (Ollama, OpenAI, OpenRouter, and similar endpoints).

UiPath agent skills for Claude Code, Codex, Cursor, Copilot, Gemini and OpenCode — RPA, UI automation, UI testing, coded agents/apps/workflows, and troubleshooting. Distributed as the UiPath Claude Code plugin.

Paigy MCP server — a voice inbox for your AI agents. Lets an agent notify a user and await their reply.

Host-neutral semantic codebase search with embeddings, symbol discovery, and call-graph tooling

Bridge Claude Code to OpenAI models — OpenAI API key or ChatGPT/Codex-plan OAuth, with prompt caching, auto-compaction, model switching, and a Claude Code binary patcher

Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.

Doc77 AI — provider abstraction layer, agent core, chat API

agent-connect — 从手机(钉钉/飞书/…)监控与控制本机多个 coding agent 会话：读写分离、信使寻址分派、写操作人工确认、Web 看板

Keyboard-driven primary-agent model switching for Pi — switch between agent profiles with Alt+Shift+←/→

OpenAI Codex provider for AgentLayer and the AI SDK. It talks to the ChatGPT Codex responses endpoint (`https://chatgpt.com/backend-api/codex/responses`) and supports ChatGPT OAuth/API-key auth through `@humanlayer/agentlayer-provider-auth`. Every factory

Swifty — CLI coding agent

AI-powered pre-commit hooks for repo-specific code quality guardrails.

Sphinx — local-first secret guard CLI for terminal + AI workflows

Aegis - local-first, policy-gated CLI agent. All effects go through a Policy Gateway; changes happen in an isolated worktree; every action is auditable.

Multi-provider AI coding agent for the terminal. Like Claude Code, but provider-agnostic with automatic failover.

OpenAI provider for Fred AI framework

Local Anthropic API powered by your Claude Max subscription. One subscription, every agent.

TradeInsight's finance & trading CLI agent for quants and traders — research the market, backtest strategies, and optimise portfolios in plain language.

Subscription usage/rate-limit command extension for pi-agent (Claude and OpenAI Codex plans).

Terminuz - The Open Source AI Coding Agent

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

OpenInference instrumentation for OpenAI Agents SDK

OpenAI-compatible streaming model provider for Truss.

Free local OSS premortem, self-heal, and no-spend Golden Loop readiness CLI for plans, launches, and installable AI agent repositories.

Standalone CLI for validating, running, resuming, and inspecting declarative agents.

In-process subagents for Pi with isolated SDK sessions, parallel and chained delegation, and inspectable threads.

konsistent is a CLI tool that enforces structural conventions in TypeScript codebases.

Docker-backed MycoMesh Provider launcher with the Consumer CLI compatibility entry point.

OpenAI Agents SDK provider for the AgentPlat runtime.

Core auth and in-memory OpenAI-compatible transport for openai-oauth.

`codelayer` is AgentLayer's reference coding agent — a multi-provider CLI (`@humanlayer/codelayer`) built on `agentlayer-core` and `agentlayer-filesystem`. It wires a `LanguageModel` (Anthropic, OpenAI, Codex, Copilot, or Fireworks/"firepass") to a filesy

The open backend for AI agents

社交关系AI管家 - 独立 CLI 工具。自动追踪社交关系，帮你拟消息、记待办、维护人脉。v3.0 起支持多 LLM provider（Claude/OpenAI/MiniMax）。

The SDK for lyra, a Sui-native policy-aware AI treasury assistant: brain, local memory + storage, the policy/approval engine, and the Sui agent keypair + chain helpers

Contract work in an enclosure: a Claude Agent SDK agent whose only tools are the contract-ops suite — no shell, no filesystem, no signing.

Badgr — run or serve GPU workloads from one command

Provider-neutral second-brain runtime and contract helpers for human and agent operators.

Optional local LangGraph runtime for Agent Kit council workflows.

A fast, cross-platform AI CLI assistant with ask and agent modes for shell tasks, file operations, and cybersecurity workflows.

Agent cli for coding and more.

Remnic memory plugin for Codex CLI — hooks, skills, MCP integration

A super basic Pi extension that toggles GPT-5.4 / GPT-5.5 / GPT-5.6 Fast mode with /fast (the default 'priority'), nothing else - one file.

Shared computation and LLM engine for geotechCLI

Self-evolving coding agent workflows for pi

Responses-compatible API bridge for Cursor Agent CLI

OpenAI provider for Standard Agents

OpenAI-compatible dynamic LLM router — a single Go binary, installed via npm as a prebuilt native binary

lyra CLI: a Sui-native, policy-bound AI finance agent. Real on-chain work gated by deterministic policy, simulation, and approval

WebAssembly/JS bindings for the llmtrim-core compression engine (wasm-bindgen).

MCP SSH Manager: Model Context Protocol server for SSH remote server management. Control SSH connections from Claude Code and OpenAI Codex - execute commands, transfer files, database operations, backups, health monitoring, and DevOps automation. NEW: Too

Versatile autonomous AI agent with three-agent architecture (Manager, Worker, Client) powered by gpt-oss-120b. Adaptive validation, full MCP support, and intelligent quality control.

Advanced n8n AI Agent node for Claude, OpenAI & Gemini — native PDF/image vision, Claude Max (Claude Code OAuth) support, Anthropic prompt caching, structured output with auto-fix, fallback models, and on-demand document fetch.

Put an OpenAI Realtime voice agent on Microsoft Teams calls. Terminates the StandIn media bridge wire protocol on one side and the OpenAI Realtime API WebSocket on the other: barge-in, function tools, on-demand vision, call governors. PCM 16k on the wire,

Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more

One-command ARCOX Agent and MCP setup for Hermes.

Pi extension that syncs models from an OpenAI-compatible API and enriches them with pricing and capability metadata.

OpenAI integration package for MLflow Tracing

autocontext — always-on agent evaluation harness

Node.js runtime adapters, workspace management, config, auth, and plugin support for afk-dev.

Unified LLM provider SDK for HoloScript - OpenAI, Anthropic, Gemini, OpenRouter, xAI, and local LLM adapters

Ory Agent Security for the Cloudflare Agents SDK — per-tool authorization, tracing, and identity propagation by wrapping the AI SDK tools passed to streamText. Built on @ory/argus.

Turn local coding-agent token usage into a satirical resource receipt, mutation creature, and containment habitat.

ConvoZen agent skills — install into Claude Code, Codex, Cursor, Gemini CLI and any agent that supports the Agent Skills spec

Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.

OpenCode plugin for auto-discovery of OpenAI-compatible models with dynamic provider configuration

Native macOS/Linux/Windows runner for the Donna orchestrator. Connects a developer machine to a Donna server and executes spec/plan/implement/verify/review stages locally.

Codex CLI for medical domain agents (fork of OpenAI Codex CLI).

nestjs-agent Vercel AI SDK v7 adapter — maps streamText to the core ModelProvider SPI (aiSdkModel)

AI SDK model adapter for the vendor-neutral Clear Ideas Agent Runtime.

Local autonomous agent control plane for software development

Persistent autonomous agent primitives for weaveIntel

MeridianOS — provider/harness-agnostic autonomous agent-orchestration core. Tenant behavior injected via a DomainPlugin.

Declarative orchestration + observability for autonomous agent loops on the Claude Agent SDK

An open-source Model Context Protocol (MCP) server and background autonomous agent designed to run the logistics of live events.

Local-first autonomous agent discovery for endpoints, repositories, and organizations