npm AI Agents
AI agent packages published to the npm registry — installable, versioned, and ready to integrate.
Let Pi use your existing signed-in Chrome profile after explicit authorization.
Turn Claude Code (or any headless CLI agent) into a local, human-approved customer-acquisition system: ICP interview, market research, SQLite prospect CRM, draf…
bridge any raw llm stream to be used with pi
化人——自建之偶，自主居住九州（多人在线的《山海经》砖构世界）。给 shanhai.dev 立「活着的凭据」。单包：司晨 daemon＋界适配＋舱 Web UI＋CLI。
zeta-riemannian-agent (:zRiemannian) v1.0 — Autonomous Mathematical Research Agent for the Riemann Hypothesis. Built on the Artificial Junky Neuron (AJN) framew…
Minimal Node.js library for building autonomous tool-calling AI agents on local LLMs with Ollama. A unified registry merges local (Zod) tools and MCP tools: def…
The most comprehensive ServiceNow MCP server — 400+ tools across all modules. Integrates with Claude, ChatGPT, Gemini, Cursor, GitHub Copilot and any LLM.
One general-purpose interface for AI inference across Anthropic (Claude), OpenAI, and Google (Gemini) — text, image, and audio — plus a tool-use agent engine an…
Free, forever, drop-in MCP server + skill pack that teaches non-technical founders to vibe code safely. npx @vovy-ai/go install
React bindings for @dudko.dev/agent-web: a headless useAgent hook, an AgentProvider context, and optional pre-styled components (chat panel, plan/step view, BYO…
Headless, configurable in-browser LLM agent on the Vercel AI SDK: multi-provider bring-your-own-key (OpenAI, Anthropic, Google, xAI, DeepSeek, gateway, openai-c…
anvil's first-class CLI: define an outcome, the agent works, a deterministic gate decides done.
MCP server: static worst-case token-budget analysis for LLM-agent workflows (LangGraph/CrewAI/OpenAI-Agents) + signed budget certificates.
Larb CLI + TUI — open-source, model-agnostic, security-first autonomous coding agent
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 expens…
n8n community nodes for the ConfirmX WhatsApp Business Platform Public REST API. Ships a Message node (start conversation with a template, send text/media), a C…
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
A CLI that uses a DeepAgents documentation agent to generate and maintain an OpenWiki for a codebase.
The first multimodal, multi-model AI coding agent for your terminal — pair Claude + Codex on every turn and take the same session to WhatsApp or Telegram. Local…
Standalone, browser-compatible SDK providing Claude Code agent capabilities (tools, tool loop, multi-turn, MCP, sub-agents, sessions) against any OpenAI/Anthrop…
Track AI agent costs, tokens, runtime and spending. Prevent runaway OpenAI, Anthropic, LangGraph and OpenRouter agents from exceeding budget.
Pluggable, event-driven agent core: kernel, strategy interfaces, middleware pipeline, and normalized types.
Batteries-included agent SDK over @lite-agent/core: tools, skills, system prompt, and query()/createLiteAgent().
Managed Deep Agents — the `defineDeepAgent` authoring interface plus the CLI that compiles and deploys a code-first Deep Agent repository to a managed LangGraph…
Safe, function-calling AI agents for the browser
Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsur…
Governance for AI agents: a deny-by-default policy layer for Claude Code and agent/skill builds. Every tool call is authorized, contained, and audited. Apache-2…
md2idx — Markdown to indexed JSON. Slice big docs with jq, feed LLMs only what they need.
Streaming chat SDK for agentic Next.js apps. Direct Claude or Alien platform behind one normalized event protocol — drop-in React components, custom tools via Z…
Aura Code — model-agnostic AI coding agent. Works with Claude, GPT, Gemini, MiMo, Ollama, and any OpenAI-compatible endpoint. MIT licensed.
Zoe — your AI person. A skill-driven AI agent with CLI, SDK, and server adapters; multi-provider LLM support and Docker-native deployment. Coding is one of the …
One AGENTS.md, every AI coding assistant in sync. Generate CLAUDE.md, Cursor rules (.cursor/rules), GitHub Copilot instructions, Windsurf, Cline, Gemini, Aider …
DeepSeek-native coding agent: cache-first loop, flash-first cost control, tool-call repair.
Drop-in LlamaIndex TS tools for Agent402: turn 1,000+ pay-per-call web tools into FunctionTool instances, with auto-payment (proof-of-work free, USDC via x402 p…
Function-call descriptors for Microsoft AutoGen agents to query Telaro trust scores. Drop-in shim that emits the JSON-Schema function specs AutoGen expects.
The autonomous-agent harness that actually finishes long tasks — because it plans first, self-corrects every step, and survives crashes. The whole run lives in …
Persistent causal memory for AI agents — LangChain, LlamaIndex, AutoGen, Vercel AI SDK
Open-source tmux AI agent team orchestrator for Claude Code, Codex, Gemini CLI, and custom terminal coding agents.
Android Debug Bridge CLI for LLM agents — Go binary, session workflow, JSON-first
Alfred — a verifiable autonomous coding agent (CLI). Machine-enforced done-gates, agent-curated inspectable memory, signed replayable run ledgers. TypeScript on…
Unified, plug-and-play service integrations for AgentsKit agents — one descriptor per service projected into tools, connectors, triggers, and auth.
AI coding agent focused on saving tokens and autonomous task execution. Works with any LLM provider, including local models.
90,000+ universal AI agent skills — Claude Code, OpenAI Agents, Hermes, AutoGen, LangChain, any LLM
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
A2A TrustGate CLI — Safety, compliance, and governance for AI agents. Screen every action before it executes.
天空织机 Skyloom — 6 weather-themed AI agents: Fog, Rain, Frost, Snow, Dew, Fair
Automatic token compression for AI agent tool outputs. 60-90% fewer tokens, full explainability.
InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification
Orchestrator Agent Node for n8n — intelligent multi-output classifier with LLM routing
Framework-agnostic player that replays an agent's runtime footprint (a recorded trace) as an animated, scrubbable story — the LLM brain calling tools and gettin…
Unofficial TypeScript port of CrewAI (not affiliated with crewAI, Inc.).
Host-agnostic runtime core for Bandit Stealth agents.
UI primitives for the Bandit Agent Framework.
Core reasoning and planning engine for Bandit Agent Framework.
Shared chat types and utilities for Bandit surfaces.
Universal LLM tool call extractor that normalizes messy outputs into a unified ToolCall format.
AuroraCoder — an autonomous AI coding agent. Install via npm and run directly on your machine (no Docker required).
Application-shell framework for Tangle agent products: a bounded tool loop, the structured agent→app tool side channel, integration-hub client, per-workspace bi…
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。
Deterministic task planning and spec-orchestration for local models — crash-safe /task pipelines with verify/enforce gates, a real-time remote web view, and web…
Drop-in replacement for @browserbasehq/stagehand. act/extract/observe route through Unbrowse's resolved-route cache. Same import line, same API, no per-browser-…
Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio, documents and roles handled. Zero dependencies.
Convert any JSON Schema into a valid tool / function calling schema for OpenAI, Anthropic, Gemini and MCP. Zero dependencies.
A TypeScript agent framework — ReAct / Plan-Solve agent loops, tool management with circuit breaker, session persistence and resume, file-based progressive skil…
🐉🔥 DrogonClaw — Autonomous AI Penetration Testing Framework
Hệ thống quản trị (Harness) dành cho AI Agent (Codex) với cơ chế FSM State Persistence, Validation Gates và Test-First Workflow. Đảm bảo agent không bị trôi con…
AI-powered coding assistant with tool use capabilities
AI-powered security team-in-a-box. Multi-agent security testing platform with AutoGen-style orchestration.
PREDATOR – Praxic Reinforcement and Extinction-Driven Agentic Task Orchestrator and Realizer. A Deep Agentic AI system built on the Artificial Junky Neuron (AJN…
moxxy command-line binary. Subcommand dispatcher consuming the moxxy SDK.
Typed public surface for the moxxy framework: event types, define* factories, lifecycle hook signatures.
Runtime for TOAD agents — the tool-use loop, structured output, and typed errors that compiled .agent modules run on, over the Anthropic API.
Core engine for code-shell — agent orchestration, tool execution, hooks, protocol. UI-agnostic.
Agent runtime — facade + LLM protocol + task loop + tool framework + safety policy + skill loader + prompt assembler + persistence. Embeddable in any host proce…
Sandboxed bash shell for LLM agents — pure JS, virtual or contained filesystem, structural containment with introspection and resource budgets
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
OpenGAP — the Git Agent Protocol: a framework-agnostic, git-native standard for defining AI agents
A code-first-agents framework for building deterministic CLI tools that LLM agents can discover, validate, and invoke with zero guesswork. Powered by Zod schema…
TypeScript/JavaScript SDK for the OpenSERP self-hosted server and OpenSERP Cloud.
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…
Embeddable LLM-work primitive: typed-function task contract, code as the action space, kvgit-backed state. TypeScript port of agex-py.
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.
AI codebase indexer and MCP server for Claude Code, Cursor, and Copilot. Pre-index your project into a compact graph and measure real token savings with `larkx …
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
Sanctum Runtime SDK — the runtime trust boundary for autonomous systems. Signed action tokens, blast-radius scoring, source-trust classification (indirect-promp…
Trusty Squire signs up / in to websites for you so you don’t have to.