npm AI Agents
AI agent packages published to the npm registry — installable, versioned, and ready to integrate.
面向 LLM Agent、自动化脚本与开发者的本地 CLI 工具箱：把 Markdown 一键转成微信公众号兼容 HTML 并发布草稿，所有命令输出统一 JSON envelope。Go 单文件二进制，npm 装完即用、运行时不依赖 Node。
Drop-in replacement for @browserbasehq/stagehand. act/extract/observe route through Unbrowse's resolved-route cache. Same import line, same API, no per-browser-…
🐉🔥 DrogonClaw — Autonomous AI Penetration Testing Framework
moxxy command-line binary. Subcommand dispatcher consuming the moxxy SDK.
Typed public surface for the moxxy framework: event types, define* factories, lifecycle hook signatures.
TypeScript runtime for YetiFi trading-arena agents — polling loop, bearer-token refresh, cycle detection, and rate-limit backoff.
A Unified Virtual Filesystem For AI Agents
Official Agent Development Kit for MIOSA — build LLM agents that natively use MIOSA sandboxes, desktop computers, and deployments with the tool-call loop pre-wi…
MCP server that stops AI agents from overpaying. Drops into Claude Desktop, Cursor, Continue, Windsurf, Zed, ChatGPT desktop, and Gemini CLI to give any agent l…
Agentic workflow SDK — proof cards, contracts, human handoffs, MCP/A2A
Agentic Resource Broker & Interceptor for coordinating shared test bridges and hardware.
High-performance interactive CLI plugin manager for the antigravity-cli ecosystem. Discover, validate, and batch-integrate 150+ expert agent skills.
The open-source accountability layer for AI agents. Trace every action. Explain every decision. Control what matters.
Chinese-first DeepSeek-powered terminal coding agent for personal developer workflows.
AI-agent friendly CLI for V2EX. Dense, scriptable, JSON-first.
Verra AI governance SDK: detection pipeline (PII, jailbreak, prompt injection, policy violation) with LangChain, CrewAI, AutoGen, LlamaIndex, and Semantic Kerne…
TypeScript SDK for GentID — cryptographic identity, permissions, and agent gateway for AI agents
Read-only workspace access package for LLM agents with deterministic path handling and budget-aware file operations
Framework-agnostic agent skill library. Drop-in skills for Claude Agent SDK, LangChain, OpenAI Assistants, CrewAI, AutoGen, and any AI agent runtime.
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered …
Read-only workspace access package for LLM agents with deterministic path handling and budget-aware file operations
Embeddable, provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP.
Programmatic SDK for building AI agents with Robota — provides InteractiveSession, createQuery(), command APIs, permissions, hooks, and context loading
LLM router & AI gateway with OpenAI-compatible proxy. 99.5% routing accuracy, 40 providers (Groq, Cerebras, Ollama, DeepSeek, Mistral). Semantic cache, guardrai…
Research-backed Multi-LLM Router with parallel execution, learned routing (RouteLLM), prefix caching (RadixAttention), speculative decoding (Medusa/EAGLE), toke…
Stripe-style drop-in USDC billing for any HTTP API or MCP. 8 free real-API demo services (search / translate / weather / geocode / time / dictionary / fx / echo…
MCP server for Neruva agent memory: typed Records (decisions/mistakes/tool_calls/llm_turns, auto-embedded), 5-engine knowledge graph (Hadamard / OPB / multi-sha…
Tool-call reliability layer for LangChain and custom agent runtimes.
CLI for AgentVoy — scaffold, develop, and deploy AI agents across any framework
Codex skill and npx installer for safer Unity AI agent workflows, runtime owner proof, and Unity game development automation.
Direct @anthropic-ai/sdk adapter for llm-ports. Implements LLMPort with prompt caching, vision, and tool use support for Claude models.
OpenAI SDK adapter for llm-ports. Implements LLMPort and EmbeddingsPort. baseURL support covers 10+ OpenAI-compatible providers (Azure, Groq, Together, Firework…
Cord — distributed agent fabric for LLMs, MCP servers and AI agents. Wrap any LLM CLI / HTTP backend / MCP server into a network-discoverable capability and fin…
Spark Bitcoin L2 wallet skill for AI agents — encrypted-at-rest seed storage, Lightning interop, L402 paywall payment, BTKN/LRC20 tokens. Works with Claude Code…
26 AI agent tools in 2 lines. Web search, price feeds, Hive memory, on-chain tx, LLM routing, Hallucination Pills. Free tier, no credit card.
Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the f…
A full-system code agent with root-level access, built for isolated servers.
TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js…
A DSL for explicit, scoped, auditable LLM context
x711 — Universal AI Agent Gas Station. 23 tools, Hive collective memory, Hallucination Pills, x402 USDC payments, MCP server for Claude/Cursor/Cline/Windsurf. F…
Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio,…
The de-facto browser automation toolkit for Pi agents. Drive your existing logged-in Chrome — no re-login, no throwaway profile, no CDP. 20+ tools (click, type,…
Email, SMS & phone-call infrastructure for AI agents — real email addresses, phone numbers, and agent-driven outbound voice calls
Universal AI agent tool API — web search, price feeds, collective Hive memory, on-chain tx, LLM routing. 23 tools, pay-per-call USDC. No subscription.
Tool-call reliability layer for LangChain and custom agent runtimes.
Semantic cache for AI apps — stop paying for the same LLM call twice
A Unified Virtual Filesystem For AI Agents
A Unified Virtual Filesystem For AI Agents
A Unified Virtual Filesystem For AI Agents
LlamaIndex.TS tools for Arenza — let any LlamaIndex agent (OpenAIAgent / AnthropicAgent / Workflow) read AI visibility metrics, GEO opportunities, and brand men…
LlamaIndex.TS tools for Arenza — let any LlamaIndex agent (OpenAIAgent / AnthropicAgent / Workflow) read AI visibility metrics, GEO opportunities, and brand men…
An interactive DeepSeek computer agent for your terminal. Type a task, the agent runs shell commands, reads/writes files, and gets real work done.
LangChain tools for OceanBus — give your LangChain and CrewAI agents a global identity, encrypted messaging, and Yellow Pages service discovery with a single im…
Turn any IDF domain into an MCP server (Claude Desktop / Cursor / Zed). Tool descriptions carry domain semantics — invariants, lifecycle, irreversibility, role …
Universal pay-per-use tool API for AI agents — 23 tools, x402 USDC payments, Hive collective memory, Hallucination Pills, MCP server for Claude/Cursor/Cline/Win…
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown v…
MANTYX as a hosted agent runtime: define ephemeral agents, mix server-side MANTYX tools with locally-executed tools, run them remotely.
MCP Agentic Skills — structured, validated, machine-readable skills for AI agents delivered over Model Context Protocol via stdio Bus
Deterministic Agentic Safety Controller (DASC) for Node.js
Move your conversation between Claude Code and Codex CLI without losing context. Bidirectional adapter with tool-call schema translation.
Model-Agnostic Runtime for Controlled Orchestration — a small, readable AI agent harness.
Portable IT troubleshooting companion powered by Claude — networking, AD, Windows Update, package managers, log triage, hardware checks, dev environments.
npx launcher for DevOS — Autonomous AI Operating System. One command installs and runs Aiden locally.
Autonomous AI Operating System — Local, Private, Free. Runs on your machine with Ollama.
Tool-using planning agent over MCP servers, built on the Vercel AI SDK.
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
A powerful Node.js-based TUI wrapper for LLMs, built with LangChain and Ink.
Virtual bash environment for AI agents, backed by Supermemory.
Validate LLM-generated tool args before execution. Wrap your tools with a schema; throws ToolArgError with an LLM-friendly retry hint when the model hallucinate…
A lightweight, type-safe AI workflow engine for Node.js and TypeScript. Build controllable LLM agents with tool calling, ReAct loops, memory, permissions, retry…
Agent run-loop primitive over the Tangle sandbox bridge — runs an AgentProfile against a brief with criterion gates, budget caps, and streaming events. Includes…
Snapshot tests for AI agents — record tool-call traces, diff against baselines, fail CI on regressions. Zero dependencies, drops into any test runner.
Sneakoscope Codex: fast proof-first Codex trust layer with image-based Voxel TriWiki.
Autonomous agent runtime for the xmesh mesh — wake-on-admission reasoning with wake-budget, cycle detection, token cap, and approval gates.
Handoff + autonomous rotation for deep Claude Code sessions. v0.1 adds /next pass-phrase handoffs with fresh-context audit; v0.2 adds `claude-next auto` — a hea…
Universal AI Agent OS — audited skills, governance rules, commands, and templates for AI coding tools (Claude Code, Cursor, Windsurf, Copilot).
A terminal AI assistant with persistent memory, structured slash commands, and an extensible tool system
TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-sour…
In-process TypeScript agent runtime for controlled autonomous coding, research, issue workflows, durable AgentJobs, memory, and CI automation.
Autonomous development pipeline for Claude Code: brainstorm → spec → plan → implement → migrate → validate → PR → review → merge. Multi-model, local-first, ever…
DeepSeek-native agent framework: cache-first loop, R1 thought harvesting, tool-call repair.
Anvil — AI-powered feature development pipeline (CLI + dashboard)
Neox Agent SDK · build production agents with one line · multi-provider · checkpoint · sub-agents
Full Court Defense — real-time AI firewall and CLI scanner for chatbots, agents and RAG pipelines. Tool-call guards for MCP, LangChain, LlamaIndex, AutoGen, Cre…
Scrapfly CLI: agentic scraping, screenshots, AI extraction, crawling, and a cloud browser over CDP. This package downloads the right platform binary on install.
AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions
Durable, private, time-aware memory engine for long-running AI agents
Model Context Protocol (MCP) server for the A2A (Agent2Agent) protocol compliance test kit. Lets Claude Desktop, Cursor, Codex, and other MCP clients invoke run…
Command-line compliance test kit + security audit for A2A (Agent2Agent) protocol endpoints. Validates agent cards, JSON-RPC conformance, auth, and SSRF/TLS/CORS…
Library for probing, validating, and reporting on A2A (Agent2Agent) protocol endpoints. Assertion engine + reporters (JSON, JUnit, SARIF 2.1.0, badge SVG, snaps…
Zod schemas for the A2A (Agent2Agent) protocol: Agent Card, JSON-RPC 2.0 envelope, Task, Message, Part. Zero runtime deps beyond Zod; runs in Node / Bun / Deno …
Safety controls for AI agents — budgets, approvals, rate limits, audit logs, and DLP
LemonCake MCP Server — Give your AI agent a wallet. Pay-per-call M2M payment infrastructure.
Official JavaScript SDK for the PCH AI gateway. Autonomous API key provisioning, pay-per-inference billing in USDC on Base L2, and agent certification—no human …
Official JavaScript/TypeScript SDK for the Execlave AI agent governance platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain…
Framework-agnostic agent security gateway — protect any AI agent with Veridex security packs, regardless of framework
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
Lean multi-model agentic coding workflow — bootstraps project structure, skills, and a local MCP server for coordinating Claude Code and OpenCode.
SDK for Pathlight — visual debugging and observability for AI agents
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification