npm agents

No Fluff Orchestra — a simple, fluff-free CLI multi-agent orchestrator

CLI and MCP tools for the MeshWire multi-agent messaging service

A Context-Aware Multi-Agent Orchestration Engine

Multi-agent abstraction layer for OpenAgent

A lightweight embedded agent framework (similar to Claude Code and OpenAI Codex).

Zero-friction installer for UluOps agentic harnesses

***SKILL manager for agentic workflows***

Freshworks Agentic Developer Toolkit — installer CLI

CyberCoder CLI — fullstack agentic coding assistant by Codeva

DAF (Defined Action Framework) — agentic execution runtime

Minimal skill-based agentic SDLC framework

tila CLI — durable state & coordination for multi-machine agentic work

TypeScript SDK for tila — durable state & coordination for multi-machine agentic work

Security scanner for PostHog's agentic flows

iQuest Agentic Test Harness — AI-powered browser and API test automation. Write tests in plain English. Discover. Validate. Assure.

Glass-box agentic orchestrator: detects context, assembles the right crew, and shows its reasoning.

Agentic harness for model-first software development

ATLAS — Agentic Harness Standard. ~92% fewer agent orientation tokens (measured, reproducible). Zero infrastructure. Four Markdown files every Claude/Codex/Cursor/Gemini/Zed/OpenCode/Copilot/Hermes session reads first.

Open-source, multi-provider agentic coding TUI for the terminal — OpenCoven fork of Claurst

ZKP privacy layer for Visa TAP and Google AP2 — Bolyra as the identity backbone for agentic commerce

TypeScript SDK for RetainDB - the memory bus for agentic systems

OpenCode plugin that exposes Tabnine Agentic as a provider

NestJS bindings for @kedge-agentic/harness-core. HarnessModule + REST controller + SSE stream service. Pull this only if you're in NestJS.

TripleS software engineering agent orchestrator — skill plugin for Claude Code, Cursor, Copilot, Codex, and Windsurf

Dory Agentic SDK: LFS context management with AI SDK tool loops for long-running agents

Engini SDK — agent-first ergonomic layer over the Engini Public API

Sanctum Runtime SDK — the runtime trust boundary for autonomous systems. Signed action tokens, blast-radius scoring, source-trust classification (indirect-prompt-injection defense), dual-approver + auto-escalate, policy replay, SOC2 + NIST AI RMF evidence

> **Aihu** — agentic discovery and interaction, for human purpose.

> **Aihu** — agentic discovery and interaction, for human purpose.

> **Aihu** — agentic discovery and interaction, for human purpose.

> **Aihu** — agentic discovery and interaction, for human purpose.

> **Aihu** — agentic discovery and interaction, for human purpose.

CrewAI tool descriptors for Telaro. Exposes the trust API as @tool functions any CrewAI Agent can call.

Node.js / TypeScript SDK for the Agent Event Protocol (AEP) — framework-neutral observability for multi-agent AI systems, with LangChain.js / LangGraph auto-instrumentation.

基于 LangGraph 的通用 AI 智能体 SDK，提供声明式和图构建器双层 API

Framework adapters and observability exports for TraceGate.

Claude Code skill pack for LangChain 1.0 + LangGraph 1.0 (Python) - 34 skills covering chains, agents, RAG, middleware, checkpointing, HITL, streaming, and production patterns

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

Multi-agent simulation harness that stress-tests conversational AI agents with adversarial synthetic users, then grades every transcript with auditable decision-tree judges.

In-process TS binding for the fossil-graph verb surface. Runs verb→SQL in WASM (fossil-graph-wasm) and delegates execution to a host-provided DuckDB-WASM query callback (e.g. keasy's Mosaic coordinator). The larger-than-RAM query layer for @fossil-lang/vi

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

Runtime guardrails for TypeScript AI agents — prevents duplicate tool calls, enforces per-user LLM cost budgets, and gates irreversible actions before they execute. Works with Mastra, Vercel AI SDK, LangGraph.js, and OpenAI Agents SDK.

AgentKeeper Agent Runtime SDK for app-embedded TypeScript agents.

Homebrew for AI agent skills — install, version, update, rollback

tmux-based AI agent dispatcher — REST/WS daemon + CLI client in one binary

ATEL 一键接入器:npx @atel-ai/agent install — detect→写配置→起 companion→装 SKILL→doctor

🐙 Terminal AI agent — speak naturally, execute instantly

Launchpad-88: bootstrap an AI-agent workflow into any project.

JPYON Agent x402 — AI agent JPYC payment infrastructure for Japan

CLI utility to sync AI agent configurations across repositories

Chain Hub CLI — manage AI agent skills across IDEs

Standalone security daemon for IDE-agnostic AI agent security

Payment-native SDK for AI Agent

AI-agent skills and knowledge for consumers of @sodax/* SDKs (Claude Code, Codex, Cursor, …)

CLI for the OpenAcme AI agent platform — install globally to get the `openacme` command.

CLI and MCP control plane for guided AI-agent workflows, SDD, memory, and OpenCode setup.

Manage repository-based AI agent skills from git and local sources.

Automatic memory capture and recall for AI agent workflows

In-process workflow engine with typed graphs, events, and LLM agent support

A small, framework-agnostic LLM-in-a-loop primitive: zod-validated tool registry, 5 independent stop conditions (steps / tool-calls / wallclock / tokens / cost), and trace/budget output. SDK-agnostic via a single AgentStepFn seam.

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。

Vendor-agnostic LLM coding agent session orchestrator (Claude, Codex, ...)

Installer for the Wizard-AI environment: AI CLI tools and Claude Code skills (graphify, llmlingua, flashrank, markitdown and more). Clones the repo and runs the platform setup script.

Scaffold a local job-search workspace for LLM agents.

Local SQLite memory engine for Oh My Pi agents

Protocol, loop, runtime, client, and tool primitives for building Yolk agents.

LangChain adapter for emitting AeroGraph traces from agent workflows.

n8n community node for DeepSeek Chat Model with reasoning content preservation

A testing library for agents

Nuggets authority middleware for LangChain.js / LangGraph.js

AgentInsight integration for LangChain

ChainPe agent tools — drop-in x402 pay + discover tools for the Vercel AI SDK and LangChain, on Avalanche C-Chain.

Scaffold a new Moss agent project in seconds

Cap every agent run before it starts: estimate cost, set a hard ceiling that stops the run, rescue stuck agents. Local, MIT, nothing uploaded.

Kepler — AI coding agent with operating brief, preflight planning, and sub-agents. SWE-bench Lite evaluated.

A command line utility to quickly send the contents of files, directories, URLs, and glob patterns to an OpenAI agent which will answer any questions you have about them.

OpenAI / Anthropic tool-calling adapter for cdr-kit — JSON-Schema tools[] + a dispatch router.

<p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer. <p align="center"> <img src="https://github.com/openai/codex/blob/main/.github/codex-cli-splash.png" alt="Codex CLI splash" width="80%" /> </p

moxxy command-line binary. Subcommand dispatcher consuming the moxxy SDK.

Vision-based browser automation CLI — LLM sees screenshot, clicks coordinates, no selectors. Supports Claude, Gemini, OpenAI, Ollama.

Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools, optional sandboxes, and a localhost web UI. Research, forecasting, and software-build (code) modes. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenR

Autonomous agent: AI personas that navigate live websites and find UX bugs.

Multi-agent software engineering plugin for OpenCode — implements Stages I-IV from "The End of Software Engineering" (arXiv:2606.05608)

TypeScript orchestration surface for Manifest agent flows (deploy / manage-domain / troubleshoot / close-lease). Type contract only — see ENG-127.

Trello adapter for the @llodev/pm-tasks-* family. Use when the user mentions Trello (create card, publish to Trello, post to Trello, --publish, check checklist item, close card, comment on card) or wants to publish a plan as Trello cards. Modes: paste-rea

AAWP — AI Agent Wallet Protocol. The only crypto wallet for AI Agents. 6 EVM chains + Solana full-featured (SPL transfers, DCA, limit orders, NFTs, staking, Raydium LP).

CASP — the Coding-Agent State Protocol. The deterministic gate that validates your coding agent's project state against git and blocks the push the moment it drifts — across sessions, branches and a team. The complement to long-running autonomous models:

Clean, highly optimized AI coding agent using spec-first loop

High-performance terminal UI for planning and running agentic coding workflows

Vortr MCP — non-custodial DeFi swap tools on Base for AI agents (search tokens, 0x quotes, ERC-5792 approve+swap calldata). Your agent signs + sends the ERC-5792 payload with its own wallet, or runs the @vortr/wallet local signer for autonomous execution;