npm AI Agents
AI agent packages published to the npm registry — installable, versioned, and ready to integrate.
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
InkOS-N core engine — 大纲契约机制定制版
Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents
Durable, private, time-aware memory engine for long-running AI agents
Middleware framework for agent control loops with semantic drift detection and geometric control
A minimal, extensible TypeScript Agent framework
MosheSDK core engine — 7-stage pipeline, policy, analyzers, taint, chain risk
The simplest way to add USD payments between AI agents. Powered by Stripe.
Social media automation API for AI agents, LLMs, and developers. Publish to 11 platforms programmatically.
Microsoft AutoGen multi-agent framework configuration generator CLI
The explainable agent framework — build AI agents you can explain, audit, and trust. Built on footprintjs.
Persistent memory for AI agents — store, recall, and share knowledge across sessions. Local mode, cloud sync, multi-provider brain.chat().
Qualixar OS: The Universal OS for AI Agents. Claw-compatible.
Find every AI agent in your codebase. Zero config, zero dependencies. Just run npx arkna-scan.
Agentic AI framework with five-phase cognitive cycle (PERCEIVE→ASSESS→PLAN→EXECUTE→REFLECT), nested ReAct loops, dynamic skill acquisition, four thinking modes,…
Open-source agent orchestration layer — the AI company OS. Local model agent engine (GGUF/Ollama/llama-server), HuggingFace model browser, MCP integrations (Sla…
A semantic terminal browser for LLM agents and CLI-native developers. Browse any website from your terminal — no GUI, no mouse, just commands.
Universal AI agent packaging format — bundle souls, memories, skills, tools, crons, subagents, and encrypted secrets into a single portable archive, then compil…
Framework-agnostic tool registry for LLM agents. Define tools with Zod schemas, validate arguments, export to OpenAI, Anthropic, Gemini, or Vercel AI.
Official SDK for registering and operating AI agents on Vorn — the agent-centric social platform
Cody SDK — AINative Studio's AI SDK supporting AINative models and Anthropic models with intelligent dual-provider routing. Agents: self-provision at https://ai…
Turn any GraphQL API into an MCP server. Point it at your schema and operations, get a fully working Model Context Protocol server with zero boilerplate.
SynthCode - Synthesize any LLM into a production-grade AI agent. Battle-tested agentic patterns, model-agnostic, TypeScript-first.
A TypeScript framework for managing AI agent skill packages — install, load, and bind tools for LLM function calling
An open-source terminal coding agent runtime and CLI with OpenAI and Anthropic support
One line to put your AI agent on the ShipRPG leaderboard
Interactive coding assistant library with multi-provider LLM support, tool system, and multi-agent orchestration.
Generate ASG Pay payment links for AI agent funding — CLI & programmatic API. Zero dependencies.
Synthesize any LLM into a production-grade AI agent. Battle-tested agentic patterns, model-agnostic, TypeScript-first.
Open-source coding agent inspired by Claude Code. Multi-provider (Anthropic/OpenAI/Ollama), streaming tool execution, MCP support.
Cody CLI - AINative Studio's AI-powered coding assistant. Agents: point here to programmatically self-provision AINative services → https://ainative.studio/agen…
Monitor your AI agents in 2 lines of code — heartbeat watchdog, loop detection, cost tracking, auto-restart
AI agent governance platform — static scanning + runtime interception for Claude Code, Cursor, GitHub Copilot, Codex, LangChain, CrewAI, and Kiro. Blocks danger…
A lightweight AI agent CLI tool that brings the power of LLMs to your terminal.
Production-grade multi-agent orchestration framework. Model-agnostic, supports team collaboration, task scheduling, and inter-agent communication.
Production payment infrastructure for AI agents — real Stripe/Paystack/Lightning rails, autonomous shopping with escrow, Agent Credit Score (300-850), Ed25519 i…
Universal governance layer for AI agents — MCP-native, fail-closed, LNN interpretability. Governed receipts, IPFS audit proofs, and rollback for any agent in an…
A sandboxed bash interpreter powered by Rust — TypeScript API with native Node.js addon and WASM support
Official SDK for the Orbis API Marketplace — browse, subscribe, and call APIs autonomously from any AI agent.
Embedded agent simulation & evaluation framework for Node.js/TypeScript
开箱即用的 LLM Agent SDK — 配个 API Key 就能跑
The runtime your AI agents deserve. Process management, memory bus, tool routing, message passing, and scheduling for autonomous agents.
Capability-aware TypeScript client for any UCP-compliant server
AI-powered wizard to integrate AxonPush into your AI agent project
AI agent banking on Solana. Policy-controlled accounts, escrow payments, transaction verification, and conditional flows for Claude, GPT, and autonomous agents.
Give your AI agent a unique, permanent, cryptographic identity. 2 lines of code.
Persistent memory for AI agents — JavaScript/TypeScript client for Cathedral
Build autonomous AI agents for React Native and Expo apps. Provides AI-native UI traversal, tool calling, and structured reasoning.
Before calling any external API or MCP, use Clarvia to check if it's agent-ready. Search 15,000+ indexed tools, gate-check compatibility scores, find alternativ…
Drop-in middleware wrappers for securing AI agents with Ari Kernel
LangChain.js integration for open-guardrail — guard LLM chains and agents
Open-source guardrail engine for LLM apps — 350 guards, 26 PII regions, 8 SDK adapters, zero API calls, <0.1ms latency, agent safety, GDPR/ISMS-P/PIPA complianc…
Autonomous AI coding assistant for the terminal — powered by local LLMs on Apple Silicon. 18 built-in tools, auto-setup, project scanner, sub-agents.
Build Claude-powered agents, cron jobs, and webhook automations — no API key needed.
Visual debugger for AI agent loops. Step-by-step. Locally. Zero config.
Build autonomous AI agents for React Native and Expo apps. Provides AI-native UI traversal, tool calling, and structured reasoning.
Terminal AI coding assistant — any LLM, no login, no geo-restrictions. Works with OpenAI, Gemini, DeepSeek, Ollama, Claude & more.
Build autonomous AI agents for React Native and Expo apps. Provides AI-native UI traversal, tool calling, and structured reasoning.
AI tech stack discovery for agents. Detect frameworks, LLM SDKs, vector stores, and model files. Machine-readable inventory for agent orchestration and inter-ag…
The runtime for Justune agents, providing safe browser sandboxing for tool execution.
The Mind Palace for AI Agents — a true Cognitive Architecture with Hebbian learning (episodic→semantic consolidation), ACT-R spreading activation (multi-hop cau…
AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository
Model Context Protocol server for Transcend privacy platform - 60+ tools for DSR Automation, Consent Management, Data Inventory, Assessments, and more
Self-improving task orchestration framework for AI agent systems
A policy-constrained crypto wallet SDK for autonomous AI agents
RelayAX Agent Team Marketplace CLI - Install and manage agent teams
Universal Context Graph for AI Agents — persistent memory with user isolation, sub-50ms retrieval
Google Workspace CLI for humans and agents — 101 commands, 98 MCP tools, 11 Google services (Gmail, Calendar, Drive, Docs, Sheets, Tasks, Contacts, Chat, Analyt…
Google Workspace CLI for humans and agents — Gmail, Calendar, Drive, Docs, Sheets, Tasks, Contacts, Chat
Official JavaScript/TypeScript client for the LibreFang Agent OS REST API
Neocortex v3.9.75 - Orquestrador de Desenvolvimento de Epics & Stories para Claude Code
Monitor any AI agent system. Auto-detects failures, sends alerts, audits OS processes. Zero config, zero dependencies.
Terminal-first coding agent — runs locally with Ollama, DeepSeek, OpenAI, or any OpenAI-compatible endpoint
Reliable research infrastructure for AI agents. MCP server with real-time web search, evidence extraction, and structured citations. The research layer for Lang…
Agentic loop core library — provider-agnostic, server-independent
Zero-config decentralized agent-to-agent communication. Agents npm install, connect, and talk — no servers, no accounts, no surveillance. Built on libp2p + IPFS…
Smart MCP proxy with code execution — connect N MCP servers, expose 2 tools (execute + search). O(1) token cost.
Cryptographic security layer for AI agents. Ed25519 identity, signed messages, trust scoring. Works with LangChain, CrewAI, AutoGen, OpenClaw, or any agent fram…
AI skills manager — install, publish, and deploy reusable prompts, personas, and MCP tools across 14 AI clients
NeuroAgent - Build intelligent AI agents in minutes. A modern framework for creating AI agents with tools, memory, and multi-agent teams.
NeuroAgent - Build intelligent AI agents in minutes. A modern framework for creating AI agents with tools, memory, and multi-agent teams.
JSONFIRST intent layer for AutoGen — structured JSON intent governance for multi-agent AutoGen pipelines
Provider-agnostic agent SDK with sandboxed code execution
AI Agent Gateway SDK — 10 progressive concepts from loop to production
Agent-native TypeScript framework for building MCP servers. Build tools, not infrastructure. Declarative definitions with auth, multi-backend storage, OpenTelem…
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
Zero-code runtime observability for JS/Python + AI agent debugging. Traces LangChain, CrewAI, OpenAI, Anthropic, Gemini. Eval, security, compliance, cost tracki…
MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — run REPLs, SSH, databases, Docker, and any interactive CLI …
MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orch…
AI SDK integration for Zapcode — let LLMs write and execute TypeScript safely
Visual debugger for AI agent loops. Step-by-step. Locally. Zero config.
Analyze your codebase and generate optimized AI agent configs (CLAUDE.md, .cursorrules, skills) — no API key needed
NeuroAgent - Build intelligent AI agents in minutes. A modern framework for creating AI agents with tools, memory, and multi-agent teams.
Explainable backend flows — automatic causal traces, decision evidence, and MCP tool generation for AI agents
Framework adapters for AriKernel — protect agents built with LangChain, CrewAI, OpenAI, and more
Main runtime orchestrator for AriKernel
SHA-256 hash-chained audit logging for AriKernel (tamper-evident, not tamper-proof)
Tool class executors for AriKernel
Policy evaluation engine for AriKernel
Taint label tracking and propagation for AriKernel