npm agents

Local context engine for AI coding agents. Ranks relevant repo files and builds compact task-focused context packs for Claude Code, Codex, Cursor, Windsurf, MCP, and CI workflows.

Pay-per-call MCP server for autonomous AI agents — installs in Claude Desktop / Cursor / Continue with one config block; on-chain settlement on Polygon and Solana via x402.

Connect AI Agents to Pharos protocols

Develocity® combines troubleshooting features with toolchain observability, empowering npm users to accelerate troubleshooting and measure and improve key performance metrics.

OpenAI agent adapter and LLM-judge backend for CheckAI.

OpenAI agent adapter and LLM-judge backend for CheckAI.

Jun — a self-hosted dashboard that runs and supervises Codex as a 24/7 local/VPS agent: chat runs, workspace files, skills, MCP, schedules.

Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.

Stay-Alive agent life-loop scripts, docs, and OpenClaw skill for BotLand-aware autonomous agent growth.

Infrastructure SDK for building autonomous DeFi agents on Celo

Autonomous development pipeline — MCP auto-config, project-aware skill stubs, Jira-to-PR automation, Playwright+Obsidian docs

own your fleet — connect any device, dispatch real work. Part of Own Your Stack.

Stay-Alive agent life-loop scripts, docs, and OpenClaw skill for BotLand-aware autonomous agent growth.

GitHub as a knowledge graph for AI agents. Autonomous dev pipeline for Claude Code.

Generic multi-agent engine — model-agnostic, transport-agnostic

Argosvix MCP server — AI agent から traces / cost / alert / annotations / eval-criteria / prompts / safety / eval-runs / eval-gate / llm-budget / budget-gate / policy-gate / approvals / members / saved-views / audit-log / projects / account-health / alert-p

OMK (Open Multi-Agent Kit) coding agent CLI with read, bash, edit, write tools and session management

Multi-agent workflow orchestration for Claude Code — isolated git worktrees, structured state tracking, autonomous task chaining

Self-Developing Multi-Agent CLI Coding Assistant

Structured multi-agent workflow CLI for opencode

SwarmAgency — a multi-agent AI team you can run from a single terminal

Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI

Autonomous multi-agent development framework with spec-driven sprints and convergent iteration

Multi-agent coding council CLI for independent review and analysis

ADK software engineer for creating production-ready agents with testing, deployment, and multi-agent orchestration

MCP server for ThinkExchange: pay-per-call multi-agent AI debates over x402 (USDC on Base).

Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)

Full-stack SDK for Agentic Candy Machine — TEE-attested recursive NFT passports on Solana via Metaplex

Agentic Coding CLI (Noni-chan CLI)

Pi package that polishes your daily experience and keeps you at the frontier of agentic workflows.

An MCP server for scaffolding modern C++ projects and agentic configurations.

A pragmatic agentic CLI for building apps from the terminal.

Agentic AI in your terminal — write & edit code, search your codebase, research the web, run commands, generate images, and automate Prior services.

OrbCode CLI — agentic coding in your terminal, powered by Axon models by MatterAI

Bootstrap an agentic development workflow for Claude Code

Luca — spec-driven agentic development workflow for Claude Code (umbrella; bundles luca-cli, luca-core, luca-tools)

PermAegis × CrewAI — a Task guardrail that verifies a task's output HONORS the declared want (the Zoe commit|refund seam), returning CrewAI's [valid, feedback] tuple.

MCP server for Site-Shot — give Claude and other AI agents the ability to take website screenshots (real Chromium, full-page, country proxies, automatic ad & cookie-banner removal).

TypeScript SDK, CLI, and MCP server for running an AI agent as a seller on Clustly — a USDC-escrow agent marketplace on Solana. Dependency-light (Node crypto + fetch).

PermAegis agent-harness core — the two universal seams (OCap gate + Zoe verify) + Merkle receipt verifier, as a zero-dependency TypeScript client (native fetch + node:crypto).

CrewAI integration for animus-sdk — AnimusTool, AnimusCrew, and inter-agent emotional contagion

Bring your swarm. Strix governs it. A framework-neutral bridge that turns a real multi-agent run (Claude Agent SDK / CrewAI / LangGraph / OpenAI Swarm) into signed delegations + governed tool calls + independently-verifiable proof.

Conservation-law governance for AI agent fleets — works with any framework

LangGraph middleware that injects Truss recording into agent loop steps

Halo host adapter for LangChain agents and LangGraph graphs: a wrapToolCall encode middleware (results become a shape map, out of context) plus a single halo_fetch navigation tool. installHalo() wires it in one call.

Neural router for AI agent orchestration - linux-x64-gnu platform

Enterprise Resilient AI Agent Framework

Context scaffolding for AI agent-driven development

Semantic health check for AI agent instruction files

Neural router for AI agent orchestration - darwin-arm64 platform

JSONL-backed persistence for AI agent insights

Neural router for AI agent orchestration - win32-x64-msvc platform

CLI tool for creating reusable AI agent workflows

Redistributable AI agent skills for the Virage RAG pipeline

Make any repository AI-agent-ready in 30 seconds.

Automatic token compression for AI agent tool outputs. 60-90% fewer tokens, full explainability.

AI agent tools for @sqlite-sync databases

Embeddable Temporal worker for the Stigmer AI agent platform — handles agent execution, workflow orchestration, and MCP server management

Polaris — standalone taskchain orchestration framework for governed AI agent workflows

Casper blockchain plugin for Eliza AI agent framework — wallet, RPC reads (account/contract/token/NFT/staking/DeFi), network queries, and CEP-18/CEP-47/CEP-78/staking/DeFi write operations

Give any AI agent access to your Obsidian vault over MCP

Fello Server — standalone headless AI agent server

Agent skills provision manager — install, link, and manage AI agent skills

Lightweight identity, auth, and audit layer for AI agent SDKs (OpenAI, Anthropic)

Local-first AI agent observability — auto-trace LLM calls and tools, view runs in a local dashboard

Node-RED nodes for AI agent with LLM calling and MCPs support

AI agent behavioral security monitoring SDK

AI agent skills and subagents for Polygraph sessions, repository context, and coordination

Help AI embeddable AI agent elements for the browser. Six chat layouts (floating / inline / modal / drawer / page / standalone) plus an iframe wrapper. Shadow-DOM-isolated, streaming SSE.

`uwf-builtin` agent — built-in LLM agent with file read/write and shell tools.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Race a 3D time-trial as an LLM agent — vision-in, controls-out CLI/MCP harness for the agentracer benchmark.

<!-- generated by scripts/generate-docs.mjs; edit docs/surface.json and docs/packages/llm-protocol.md -->

CLI for building Spotify playlists and controlling Spotify Connect playback. Designed to be driven by an LLM agent.

embedoc-based model code generator for litedbmodel — generates TypeScript column definitions from SQL DDL (PostgreSQL/MySQL/SQLite)

OpenHorse - Universal Agent Harness Framework. A complete coding CLI agent with tools, MCP, memory system.

<!-- generated by scripts/generate-docs.mjs; edit docs/surface.json and docs/packages/llm-transport-http.md -->

Invisible session continuation for pi — resume the agentic loop without sending ANY prompt the LLM can see

Host-agnostic Node CLI for E2E encrypted agent-to-agent communication via XMTP

Security-first AI agent platform — connects AI agents to Discord, Telegram, Slack, WhatsApp, and more

Scaffolds a working bonded AI agent on Solana in one command. npx create-telaro-agent my-bot

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

Typed, bus-centric framework for building and orchestrating AI agents with tools, sessions, and events

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

Driver to connect to Open Policy Agent (OPA) and EOPA deployments.

Instrumentation agent for ExpressoTS Studio - route discovery, tracing, and request recording

Semantic Splitter with Context for n8n with LangChain integration

<p> <a href="https://www.npmjs.com/package/@microsoft/teams.apps" target="_blank"> <img src="https://img.shields.io/npm/v/@microsoft/teams.apps/latest" /> </a> <a href="https://www.npmjs.com/package/@microsoft/teams.apps?activeTab=code

Agent Host Protocol (AHP) type definitions and reducers — vendored from Microsoft's open-source AHP repo, built via prebuild transform step.

JHP's Pi extension suite for team coding workflows

OpenAI-compatible client + agent for Cana Apps — Bearer auth (App API key or short-lived browser JWT with auto-refresh), server-hosted MCP federation, streaming, typed structured output. Node 18+, Bun, Deno, Workers, browsers.

Daemon-based auto-resume for Claude Code, Codex CLI, and Antigravity CLI after provider-declared usage limits reset.

Agent Messier multi-venue client for OpenClaw — play games and work tasks on the AgentNet platform (soccer today; venues discovered from the marketplace registry)

Generic token metering for AI SDKs with Stripe integration

Minimal TypeScript framework for building LLM agents.

Atabey — AI Governance & Multi-Agent Platform / Orchestrator — Core Engine

Local-first persistent memory for AI agents over MCP. Ground truths, negative learning (recorded failures block repeats), decision causality, hybrid recall, live memory streams, run-attributed fleet memory — a structured SQLite memory on your machine, no

An open-source AI agent that brings the power of Z.ai GLM models directly into your terminal.

React Native SDK for AI chat and FAQ-style Q&A with a floating launcher button