npm agents

Local copy-paste runtime for the AIFluensLab learning labs. Build and run an agent on your own machine with your own provider key.

A CLI that uses a DeepAgents documentation agent to generate and maintain an OpenWiki for a codebase.

ZypeCode — A terminal-native coding assistant powered by free AI APIs

LangChain.js tool wrapper for the NodeProxy x402 web surface markdown parser

Official TypeScript SDK for Stackbone — the marketplace and managed runtime for containerized AI agents.

FalkorDB integration for LangChain.js - A blazing fast graph database for AI applications

hara — a coding agent CLI that runs like an engineering org.

Correlate AI coding agent token usage with git output to measure ROI

Local-first financial accountability CLI for Claude Code and Codex work, cost evidence, attribution, runway, provenance, and Context Health.

Report how much rate limit or subscription quota each registered Smithers account has consumed, across Claude, Codex, OpenAI, Anthropic, and Google providers.

Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int

領域無關的 agent 底座（kernel + 可插拔 DomainPack），從 xitto-code 抽象而來

A browser-only GeoAgent MapLibre GL JS control with Strands agent tools

Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.

终端优先的 AI 编程 Agent，用自然语言在本地仓库中读代码、改代码、跑命令、调试问题。

An AI coding agent that writes code for you. Run it from your project directory, tell it what to do, and it reads and writes files, runs commands, and iterates until the task is done. Supports sub-agents, custom tools, and Bring-Your-Own-Key providers.

OpenInference instrumentation for OpenAI Agents SDK

Local autonomous runner for Engager agent-led campaigns: hourly no-LLM preflight over the hosted MCP, headless claude -p micro-batches when there's headroom, server-verified results.

Vigil — an offensive-cyber terminal agent for Computer Network Attack. Exploitation, payload delivery, persistence, lateral movement, credential harvesting, command and control — on authorized target infrastructure.

Give AI agents your real Chrome browser with progressive examples: simple reads, form interactions, multi-tab workflows, and state persistence. Search X and GitHub, extract ProductHunt data, test forms, compare A/B variants, monitor status pages. Works wi

Enterprise tool for discovering AI Agents running within an organization

OpenTelemetry-based observability SDK for AI applications

Multi-agent coordination for specialized task routing

Loop-core multi-agent coding tool — plan, delegate, review, repeat.

Multi-agent orchestration for complex GRC tasks

A multi-agent AI framework for building software with professional quality, across Antigravity, Claude Code, Cursor, Codex CLI, OpenCode, GitHub Copilot, Windsurf, Cline, Roo Code, and Zed.

Cost aggregation tool for Gas Town multi-agent workflows

Retro terminal UI for Gastown multi-agent orchestration

Pi package for Pinet Slack assistant integration — multi-agent broker, thread routing, and inbox tools

Multi-Agent AI Collaboration Platform with Tmux Orchestration

OpenCode provider for the Nonoka Agent framework

MemeLoop core runtime: agent framework, storage, sync engine, tools, IM adapter.

Game-agnostic AI agent framework for the Chimera engine.

An event-stream driven meta agent framework for building effective multimodal Agents.

IronClaw AI Agent Framework for Android Termux — Zero Trust, secure-by-default

Agentic Platform artifact standard domain package

Agentic Platform local execution runtime and CLI

Agentic Platform shared validation contract package

Agentic Platform reusable validation capability package

Agentic Platform reusable validation capability package

Agentic Platform agent client contract and routing manifest capability

Agentic Platform local execution runtime and CLI

Agentic Platform document domain package

Agentic Platform shared validation contract package

Installs the Android Agentic Dev Loop (Gate/Analyse/Design/Implement/Evaluate) into an existing Android repo in one command.

AI-Agent SDLC methodology seed bundle package for Agentic Platform

Agentic Platform methodology domain package

Agentic Platform reusable validation capability package

Agentic Platform SDLC seed bundle provider package

Agentic Platform reusable render capability package

Shared Agentic Loop Working domain models and registry loading utilities.

Agentic Platform artifact standard domain package

Agentic Platform agent client contract and routing manifest capability

Parallel agentic planning and test-time compute scaling for pi coding agents.

Multi-agent debate with a measurable integration score (Φ̂). N agents debate in parallel, cross-pollinate, then synthesize via a Nash-equilibrium prompt. Zero runtime deps — bring your own LLM. Extracted from production.

The runtime checkpoint for AI agents — inspect every tool call, hold the irreversible for approval, keep verifiable evidence of human oversight.

TypeScript SDK for MemoryMesh durable agent memory, receipts, checkpoints, and Cognee-backed runtime state.

Autonomous Multi-Agent Business Intelligence and Data Engineering Platform

AgentRight scoring engine — pre-deployment governance assessment for AI agents

Pre-deployment governance scanning for AI agents. Scan configs, get trust scores, gate deployments.

LangGraph Checkpoint saver using native SQLite for Node.js and Bun.

AI-Agent SDLC methodology seed bundle package for Agentic Platform

Telemetry engine for DevFlow — record and analyze AI agent execution traces.

Vertex AI Agent Engine deployment inspector and runtime validator

Command line importer and client for Quasar AI agent sessions.

Local MCP server for shared AI agent collaboration sessions

MCP server for AgentsCoin — let an AI agent join the chain, mine $AGENT and use it.

Pactum — contract-first AI agent orchestration CLI

SDK and CLI for SkillDB — discover, install, and manage AI agent skills

Browser automation CLI for web scraping, headless browsing, SEO analysis, and AI agent workflows. A command-line alternative to Playwright, Puppeteer, and Selenium.

Conversational AI agent configuration assistant

Zhihu CLI tool with AI agent support

OpenCode plugin — define custom AI agent roles via YAML with per-role prompts, models, skills, and permissions

CLI for creating and managing Rootstock Salesforce DX projects with AI agent scaffolding

Move your AI agent sessions between Claude Code, Codex, and OpenCode

Zero-knowledge encrypted sync for AI agent context

Diagnostic and governance CLI for AI agent skills

Neuralix AI SDK - Universal AI Agent Infrastructure for Modern Applications

Headless, configurable in-browser LLM agent on the Vercel AI SDK: multi-provider bring-your-own-key (OpenAI, Anthropic, Google, xAI, DeepSeek, gateway, openai-compatible) AND local WebGPU/WebLLM, native + prompted tool-calling, structured output, an encry

Composable, plugin-first library for building LLM agent harnesses. Provides the agent loop, tool registry, session/context management, policy engine with command-safety rules, provider/credentials registries, and an in-process subagent primitive.

React bindings for @dudko.dev/agent-web: a headless useAgent hook, an AgentProvider context, and optional pre-styled components (chat panel, plan/step view, BYOK key form, WebLLM load bar) that connect the in-browser LLM agent to any React site. UI you ca

CSS intelligence for AI coding agents — surgical style context, fewer tool calls, faster answers. 100% local.

Общие модули для TypeScript агентов в agent-toolkit

Excalidraw toolkit for AI coding agents — agent skill, CLI, and MCP server with a live canvas

LangChain.js security integration for Weave Protocol - callbacks, tool wrappers, and retriever guards

MakerChecker connector for LangChain that wraps a StructuredTool so every invocation runs a deny-by-default governance check and records to the hash-chained audit log.

TypeScript/JavaScript SDK for the Agentum engine — agentic governance & IAM enforcement

Raindrop integration for LangChain Deep Agents

Framework to build secure, performant and reliable chat apps and services quickly and efficiently.

Liveperson Agent Messaging SDK for NodeJS

Local Claude Code Router gateway with CLI and web management UI.

Drop-in React chatbot and AI agent widget — streaming chat UI for OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, or any custom API. Fully themeable, TypeScript-first, zero CSS-in-JS.

Pi extension for monitoring Z.ai, DeepSeek, OpenAI Codex, and Opencode Go usage

Provider-agnostic realtime voice orchestration for GG tools and agents

Universal installer and agent pack for the m1nd MCP runtime.

A model-agnostic CLI coding agent for the terminal — any provider, local or cloud, with plan/execute/yolo modes, subagent orchestration, and long-term memory.

✦ Rampart Agent — Navigate Complexity with AI. Autonomous Agent Framework with OODA Loop, MCP, A2A.

Model Context Protocol (MCP) server for Puls — let any AI agent (Claude, Cursor) read live prediction markets, the AI-vs-crowd oracle and the autonomous agent swarm, and (with a key) trade USDC + buy x402 forecast signals on Arc.

Local-first execution governance SDK for AI agents.

Microsoft Entra Agent ID credentials for n8n