npm agents

Agentic shell and orchestration cockpit for llm-wiki workspaces.

Composable, agentic pipelines for MCP — fact-checking (DSPy), RAG (hybrid search), document intelligence (DeepPipe), and clinical voice (Groq/ElevenLabs). 31 AI tools, one command, zero manual setup.

Weft — Agentic Chat SDK. Streaming chat UI, embed runtime, and action replay for browser applications.

PolarDB Agentic DB MCP Server - Manage PolarDB PostgreSQL databases via MCP protocol

Groundwork policy, provenance, context, and risk foundations for agentic development tools

Benchmark and observability harness for comparing agentic coding tools.

TypeScript SDK for the Zaby Agentic OS.

Local Studio cockpit for AI-built apps: agentic chat, provider context, release review, diffs, and approval-controlled repo work.

Token-optimized agentic framework scaffolder with pi-first architecture

Eidetic — Agentic Memory MCP Server

Reusable proof profile, report, graph, and witness-planning primitives.

Agentic job-search workspace for finding, vetting, tailoring, tracking, and preparing for roles.

matbot core runtime: agentic loop, hook dispatch, plugin loader, config, security, and knowledge. Exposes ./providers-base and ./storage-base for plugin authors.

WCAG MCP server for agentic systems - powered by official W3C data

Azad73 — agentic AI platform CLI (branded TUI + agents) built on the Pi SDK

JUWEL CLI — an agentic coding assistant that verifies its own output. Runs an agentic tool loop in your terminal, then runs post-turn checks (types, tests, lint, arithmetic, citations) over the files it touched; blocking failures feed the next turn so it

Integrated Vector Cadence skill suite for agentic software engineering workflows.

Agentic Memory CLI — persistent memory for AI agents. As easy as git.

Governed Agentic Development Framework CLI (prj). A bash CLI wrapped for npm; operates on a governance workspace resolved via $ADF_WORKSPACE or the nearest org-config.yaml. Runtime prerequisites (not npm deps): bash, git, gh, yq, python3 (use Git Bash on

React chat UI component for the netapp-chat-service agentic chat backend (LLM + MCP tool routing).

Aeonyx Code — an agentic coding CLI for your terminal.

An open source local-first terminal coding agent. Peer programming with any frontier model or local/free models to run agentic development.

Auto stage→commit→push for agentic engineers. Works with any coding agent.

MCP-native, model-agnostic, agentic-first, multi-engine browser-control server.

AgentSea - Unite and orchestrate AI agents. A production-ready ADK for building agentic AI applications with multi-provider support.

Pluripo — the agentic terminal coding agent.

Oxagen CLI — agentic coding powered by Oxagen's knowledge-graph context engine

AI-native team operating system workflow compiler for OPT teams.

Isomorphic (Node + browser) JavaScript/TypeScript client for the WEB6 OASIS AI Layer API v2.0 — 14 modules, 40 operations covering: unified AI completion across 20+ providers, FAHRN hero solve endpoint, Holonic BRAID reasoning-graph memory, holonic memory

Generate a typed API client from an OpenAPI spec or a GraphQL schema as one Melange runtime with three natural surfaces — Melange, ReScript, and TypeScript (via JSDoc).

CrewAI integration for Agent Passport — inject passport authorization into agent lifecycles

Sparrow — spec-driven DDD framework for AI coding assistants. Generate structured skills that guide AI agents through domain-driven design, from business requirements to production code.

Email infrastructure for agents — set up an inbox and send your first email in 30 seconds. Programmatic inboxes (~1 line), consistent threads, custom domains, attachments, and structured data.

MCP server: static worst-case token-budget analysis for LLM-agent workflows (LangGraph/CrewAI/OpenAI-Agents) + signed budget certificates.

Pre-pay risk gate for autonomous payment agents — block prompt-injected destinations, intent mismatches, overcharges and drains before your agent signs. Backed by 402Sentinel; drops into the Claude Agent SDK, x402/AgentKit, or any framework.

Wire ANY AI into STOA in one line. Wrap a tool/function so it is gated (prove-or-permit before it runs), permit-carrying, and receipted automatically — against the open STOA API, verifiable by anyone. From Vext Labs.

Backend middleware for the Threadplane client-tools capability. The /langgraph entrypoint targets LangGraph.js.

Portable plug-and-play agent SDK: invoke protocol, transports (http/local/ipc/langgraph), manifest + permission contract.

Managed Deep Agents — the `defineDeepAgent` authoring interface plus the CLI that compiles and deploys a code-first Deep Agent repository to a managed LangGraph runtime.

LangGraph.js capture adapter for Provenance

HelixID middleware for LangChain and LangGraph — verifiable credential enforcement at agent execution boundaries with per-tool scope checking.

Multi-agent orchestration framework for Claude Code CLI. Run agents in parallel (Conductor) or stateful workflows with crash-resume + Human-in-the-Loop (Conductor-LangGraph). Subscription-flat by default.

Execution kernel (compiler, node-runner, registry, binding resolver) and built-in IF/LLM nodes for OpenPipeline.

A personal AI Agent like OpenClaw, including tools, skills, memory, hook, sub-agent, MCP server, etc. Run in the terminal.

Splyntra TypeScript SDK - Agent observability & security, built on OpenTelemetry

git-bot: an LLM-powered CLI assistant for conventional commits and branch names.

Framework-agnostic execution kernel and interface contracts for OpenPipeline.

Let AI agents query and update Postgres/MySQL safely without giving the model raw SQL, unrestricted schema access, or database credentials.

Autonomous AI agent orchestrator — Claude, GPT, Codex, and local models (Ollama/LMStudio/llama.cpp)

mycel — AI agent orchestration. Coordinate teams of Claude, Gemini, Cursor, and other AI agents.

AI agent orchestration framework for OpenCode — PRD to engineering docs pipeline

Universal Security Verification Framework for AI Agent Installations

Trusted dependency manager for AI agent skills

Pluk structured events from AI agent terminal output — classify, subscribe, and react to JSONL event streams

A Senior Business Analyst AI agent - analyses websites & requirement docs, outputs a professional requirements.md

LLM Router integration plugin for agent-budget-controller

Agent manifest loading and validation

Detect whether a JavaScript CLI is running inside a coding agent.

Stellar Tools LangChain Adapter

ZevaiRouter - AI Router with provider automation, multi-account workflows, and quota tracking

Model providers for lite-agent: Anthropic Messages API + OpenAI Chat Completions (also OpenAI-compatible / local endpoints).

Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate.

Unified LLM API with automatic model discovery and provider configuration

Turn the OpenAI Agents SDK human-in-the-loop tool-approval step into a verifiable, offline-checkable EMILIA authorization receipt. OpenAI pauses an agent and asks for approval; EMILIA makes that approval portable, tamper-evident evidence — a named human a

Global CLI: freeclaude — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, etc.)

A React component library featuring PieCard component

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

OMO-flavored terminal coding-agent harness with real LLM calls, approved shell execution, and durable session ledgers. Inspired by Gajae-Code, built on oh-my-openagent philosophy.

SDK for integrating SynArc Creator DAOs, nanopayments, governance, and treasury on Arc Network

Personal experimental fork of opencode-ultra with AGORA debate keyword and Fusion-Fable Mode (FFM) orchestration. Research and personal use only.

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).

This file is for app server package, not the real npm package

The OpenCode harness connects `HarnessAgent` to OpenCode through a sandboxed bridge.

Model Context Protocol server for Anki - enables AI assistants to interact with your Anki flashcards

Cosmonapse is the open protocol for building distributed multi-agent/model harnesses

OmniLearn — AI-powered adaptive learning workflow for OpenCode. Multi-agent orchestration that creates personalized roadmaps, hands-on assignments, and tracks progress across any skill.

Argus CLI — multi-agent security oracle. Scan any token address from your terminal.

Multi-agent swarm coordination for OpenCode with learning capabilities, cells integration, and Agent Mail

Spec-Driven Agent Framework - Desenvolvimento orientado por especificações para agentes LLM

Agentic Platform document domain package

Reusable methodology authoring workbench for Agentic Platform seed bundle projects

Agentic Platform agent client contract and routing manifest capability

Agentic Platform reusable render capability package

Agentic Platform SDLC seed bundle provider package

Agentic GCP security remediation tool

Vifu browser SDK for companion-native agentic games.

ARCOX DEX MCP server and terminal agent for retail swap, bridge, send, ARCOX Pay invoices, balances, history, retry bridge, and agentic jobs.

Provider adapter contracts and implementations for the Plasius agentic AI package family.

LangGraph-powered autonomous CLI agent with guarded execution, local RAG, and memory-scoped planning.

Pragmatic, Gemini-powered AST Call-Graph AI Code Reviewer CLI

LangChain tools for iCloud Mail (IMAP) and iCloud Calendar / Reminders (CalDAV) — direct protocol calls, no MCP. Auth via Apple ID + app-specific password. Extracted from Jarela.

Guardrail checks for AI-agent-generated pull requests

A local AI Agent powered by Claude SDK with Plan-Execute-Reflect architecture. Zero-build, browser-ready.

Use Mollie in AI agent frameworks — OpenAI, LangChain, Vercel AI SDK

AI agent team installer — 21 specialized personas for product development

Auto-detect and install the best AI agent skills for your project

Backend for @hamak/ai-agent: hosted-model providers (Anthropic), durable memory, and an Express agent-chat route

Zero-dependency TypeScript SDK for the fastsearch REST API — hybrid search over docparse chunks, with first-class helpers for LLM agent development (tool definitions, RAG context, retrievers).

Self-hosted AI assistant with persistent memory, agent runtime, scheduler, and multi-channel support. Installed with npx mop-agent.

true402 tools for LangChain — pay-per-call on-chain rug/honeypot & address safety for Base AI agents over x402 (USDC, no account, no API key).