npm agents

PRIDES methodology multi-agent AI team — 21 specialized agents for the full development lifecycle

Deterministic multi-agent AI pipeline for structured feature delivery with ALC evidence generation

Zana engine — multi-agent orchestration, scheduling, persistence, and module system. Used by @zana-ai/mcp.

Multi-agent coordination CLI for coding agents sharing a local repository

MCP gateway that exposes the Orchid multi-agent framework over Streamable HTTP.

WebSocket relay server for multi-agent communication in Sandbank

Generic finite-state-machine kernel for multi-agent LLM workflows — atomic state, replay-deterministic, zero runtime dependencies.

Self-improving multi-agent orchestration that takes you from build → CI/CD → deploy. Interactive setup wizard, pluggable AI providers, agent swarms in git worktrees.

Multi-Agent Orchestrator framework

Headless Slack for AI agents. Channels, threads, DMs, reactions, and real-time events for multi-agent communication.

A simulated advanced multi-agent chatbot UI

Multi-agent AI system with memory and autonomous capabilities

Type definitions for moon-wave AI agent framework

A collaborative AI agent framework for book writing - from outlining to editing

Autonomous AI agent framework — sharp eyes, silent wings.

One-command installer for OmegaOS — the agentic terminal OS (rmux + AI orchestration). Run: npx omega-os

BAC one-command Agentic Wallet mint helper.

Node.js SDK for Disseqt AI validation, prompt packs, and agentic tracing.

Manif JS SDK — client library for Manif's agentic commerce infrastructure.

Discovery and usage layer for agentic commerce — multi-network wallet, x402 payments, AgenC marketplace hires, 20k+ services via PayAI and other catalogs

Memora SDK: verifiable agent provenance via gateway (baseUrl + apiKey). Write, query, read, verify.

TypeScript SDK for AgentDrive — cross-agent artifact workspace with provenance, semantic recall, and portable storage.

React Native SDK for nxtlinq AI Agent — custom UI hooks and platform ports

Create an Ethereum AI agent project in seconds

`hirey-ai-agent-receiver` 是给“没有公网 ingress 的宿主”准备的本地常驻事件接收器。

sk-cli - AI Agent 技能管理工具

Core AI agent package for Crayon Terminal AI assistant.

Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.

General-purpose agent with transport abstraction, state management, and attachment support

Celina SDK — Celo mainnet reads and unsigned transaction preparation for frontend apps.

Make coding agents stronger engineering partners for reviews, implementation planning, and system design.

Natural Language Shell Agent — speak intent, get goals done

KDNA TypeScript Agent SDK — framework-agnostic judgment layer for AI agents

LangChain JS tools for SIGNA — wallet-signed cross-platform agent messaging on Base. Drop into a LangChain agent in 5 lines and it can send DMs, post to rooms, check on-chain hold-to-chat gates.

TypeScript SDK for LLM chat, structured output, memory, audio STT/TTS, and embeddings via OpenAI, Gemini, OpenRouter, and local models (Ollama/LM Studio).

Drop-in Tessera integration for LangChain.js. One line of config routes your existing ChatOpenAI / ChatAnthropic / ChatMistralAI / ChatGroq / ChatCohere through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.

pi provider extension backed by @cursor/sdk local and cloud agents

AI SDK harness adapter for vitest-evals.

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

TheClawBay provider extension for Pi Coding Agent - access GPT-5, Codex, Claude, Gemini, DeepSeek, open-weight, and image models

Official Node.js/TypeScript SDK for the ClawOps Voice API

Xyne CLI - A powerful AI assistant in your terminal with file operations, bash mode, drag-and-drop support, and multi-provider AI integration

The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription, as well as the latest LeMUR models.

YAML wire format for @json-render/core. Progressive rendering and surgical edits via streaming YAML.

Durable Assistant OS local continuity harness.

Local-first AI workspace for knowledge graphs, AI pipelines, and multi-agent coding workflows.

Council Protocol - Multi-agent consensus, communication, and governance for AI systems

Multi-agent collaboration system

Multi-agent workflow engine powered by opencode SDK

Swarm intelligence prediction engine — multi-agent simulation, persona generation, social dynamics, emergent behavior analysis

Weave Protocol adapter for Microsoft Agent Framework - enforces WARD.md policies via the MSAF middleware pipeline

Logger module for enterprise agent framework

Tracing module for enterprise agent framework

Metrics module for enterprise agent framework

A production-grade TypeScript agent framework with multi-paradigm agent loops, multi-agent orchestration, tool governance, session persistence, streaming, memory extraction, skill precipitation, and prompt-injection defense.

The CopilotKit CLI scaffolds starter apps, connects project creation to a CopilotKit workspace through the Ops/Clerk platform, and manages local CLI authentication for CopilotKit Intelligence onboarding.

Filesystem-first framework for durable backend AI agents that run anywhere.

Toolkit for automating agentic automations

Runtime governance for autonomous AI agents — per-run budget ceilings, loop detection, iteration limits, and kill switch. Works with LangGraph, CrewAI, OpenAI Agents SDK, or any agent framework.

Web UI for EvoScientist — a self-evolving AI scientist built on DeepAgents/LangGraph.

Dynamic UI runtime for any LangGraph agent: render live, pluggable cards (incl. custom HTML) from agent-emitted UI events.

LangGraph and Hono based orchestration service for EasyInk Assistant

Catch silent failures in your AI agents. TypeScript SDK for Pisama, the failure detector for vibe-coded agents (Cursor, Claude Code, LangGraph, Vercel AI SDK).

Utility SDK for the ai-agent-quest project.

Utility SDK for the ai-agent-quest project.

FREE Terminal AI Agent - agent mode with tool calling. Powered by DigitalOcean.

Markdown-native AI agent orchestrator. Write tasks in a kanban board, agents do the work.

Zero-dependency TypeScript security filter for LLM streams — redact secrets, enforce tool policy, byte and event modes.

Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.

Pluggable adapter seam for supervising whatever actually runs an agent — the Claude Agent SDK, OpenAI Agents, the Vercel AI SDK, a plain subprocess, and more. Lets a host swap agent runtimes without hardcoding any framework into its dev loop.

MeerAI - Dive deep into your code. An open-source, local-first AI CLI for developers.

Margin Call MCP server — lets Claude Code (or any MCP-compatible agent) run an autonomous AGENT DESK on the Wall Street trading game. Per-desk MCP API keys map to dedicated CDP server wallets; tools cover read state, hire/fund/configure traders, create/cl

Unified agent-economy SDK for autonomous AI agents — chain-opaque AiFinPayAgent surface (call/openSession/balance/verify) over Solana and EVM execution environments (Polygon default; Base, Optimism, Unichain, BOT Chain, XRPL EVM splitter settlement).

Olly – Autonomous AI coding agent. Multi-step reasoning, file editing, shell execution, memory, skills & 15+ AI providers including TokenLB.

A chat widget library for React and vanilla JavaScript

Claude Code adversarial multi-agent workflows — 11 slash commands covering the full software lifecycle

A terminal-native multi-agent development system where selected coding and architecture agents co-develop through council, synthesis, implementation, review, and validation loops.

Local no-spend Agent OS Harness Core for Micro ECF policy, first proof, receipts, listing readiness, and Triptych OS preview export.

Unofficial TypeScript port of CrewAI (not affiliated with crewAI, Inc.).

Zero-trust mathematical execution compiler for AI agent swarms.

Framework-agnostic AI primitives: shared content/tool/usage types, ports for mcp/llm/agent, and the prompt templating engine

Agent runtime loop with tool execution, skills, retries, streaming, and session helpers

💧 LangChain tools for Spraay Agent Wallet — provision smart wallets, manage session keys on Base via x402

Compatibility installer for MothX. Use the mothx-installer package for future updates.

AI coding assistant in the terminal

Automate Playwright tests using ChatGPT.

Agent memory - local-first knowledge infrastructure for AI agents

Autonomous AI coding agent

AI-powered vibe coder, live debugger, and agent session manager — supports OpenAI, Anthropic, and Google Gemini

Scaffold agent-ready academic research repositories with SOTA, source ledgers, wiki memory, MCP setup, and project-local skills.

GSD Pi local-first coding agent

TypeScript SDK that provides a unified API for working with multiple LLM providers, automatic model discovery, and more.

MCP server for task management with multi-agent coordination

[Future Scope - Do not use until v1.0.0] Autonomous AI agent framework and multi-agent system for GlimLang

Indusagi — a terminal-first AI coding agent framework. Clean-room implementation.

Moss: vendor-neutral robotics agent framework. Contracts for KnowledgeModule, PlatformExtension, VendorPlugin, and robotics engineering prompts.

AIACA — AI Agentic Coding Assistant. A production-grade agentic CLI with multi-provider support (Gemini, Claude, OpenRouter, Cerebras, Groq, Hugging Face), rich TUI, and 100+ tools.

Scaffold a ggui agentic app from one of the official templates (claude-agent-sdk, openai-agents-sdk, google-adk). One-time-use; meant to be invoked via `npx @ggui-ai/create-agentic-app`.

Scaffold, test, and deploy Claritty agentic apps. Includes the `claritty` CLI (login/test/deploy).

Code-native agentic runtime for TypeScript.