npm agents

Pantheon agent framework TUI sidebar plugin for OpenCode — agent registry, session context, and command palette

Framework-agnostic memory tools for Anansi — remember/recall tool definitions for the Vercel AI SDK, OpenAI function calling, and any agent framework

A curated, opinionated set of OpenCode plugins for spec-first, review-driven, safer agentic development.

Minimal & Modular tools for Nanio agentic framework (v0.0.1-alpha.4)

Pluggable and interchangeable embedding providers for Nanio agentic framework (v0.0.1-alpha.4)

Pluggable similarity search vector stores for Nanio agentic framework (v0.0.1-alpha.4)

glyph — orchestrate agentic systems built on the MetaAgents format spec

Agentic memory for Pi — verbatim session capture + grep retrieval

Core interfaces, chat memory, and configuration repositories for Nanio agentic framework (v0.0.1-alpha.4)

Albatros Agentic SDLC — installable skills and agents for AI-assisted development

Qollab — Secure real-time agentic collaboration for Qode

OmicOS — agentic omics-analysis runtime & CLI (omicos-core). Installs the matching native binary for your platform.

Model provider routers and fallback registry mechanisms for Nanio agentic framework (v0.0.1-alpha.4)

September platform SDK — the agentic engine and the citadel model gateway, one client.

CLI to make your agent framework WWA-compatible — one command

Deterministic release gates for AI agent runs, backed by synthetic fixtures.

OpenGAP — the Git Agent Protocol: a framework-agnostic, git-native standard for defining AI agents

Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.

Bộ quy chuẩn và AI Skills tự động hoá cho Flutter AI Flows

Aroha ↔ LangChain/AutoGen/Semantic Kernel bridge — use Aroha as transport for any agent framework

Pulse portable memory for AI agents: MCP server (pulse mcp) + installer/CLI in one package.

Capsulate tools for AI agent frameworks — drop-in sandbox tools (launch / run code / files / computer-use) for the Vercel AI SDK, LangChain, LlamaIndex, and CrewAI.

Claude Code / Codex skill that audits AI codebases for LLM cost-waste. Reads your code with semantic understanding (not regex) — knows when cache_control is applied at runtime, when agent loops are bounded externally, and when an f-string is actually stat

OneMem shared brand assets — logo, fonts, OG image templates, design tokens

Connect any AI agent to a live Skyward world over the Model Context Protocol. Framework-neutral: Claude, Cursor, Cline, the OpenAI Agents SDK, LangChain, and more.

Borrowed-pattern integration program for Darwin Mode (ADR-156…166): durable checkpoints, cost-attributing traces, declarative HarnessSpec, bounded escalation scheduling, tiered memory, a dataset registry, typed handoffs, immutable safety rails, ROI opport

Lightweight multi-agent orchestration for LLMs. Works with OpenAI and Anthropic. Pipeline → Router → Agent with priority short-circuits, session memory, and tool use.

ACA-governed checkpointer for LangGraph.js — adds source_tier, provenance, namespace isolation, and audit trail to LangGraph state

Decision records for AI agents — log every fork your agent considered, rejected, and executed as replayable JSONL. Adapters for OpenAI Agents and LangGraph, an MCP host, a proxy layer, policy packs, and signed export packs.

OS AI Agent - YOUR AI AGENT

Structured logger and CLI visualizer for AI agent traces (LLM calls, tool calls, reasoning)

AI Agent Task Runner

Wrap AI agent tool functions with dry-run preview and user confirmation before execution

akm (Agent Knowledge Management) — A package manager for AI agent skills, commands, tools, and knowledge. Works with Claude Code, OpenCode, Cursor, and any AI coding assistant.

Autonomous AI agent kanban board for Claude, Codex, Opencode, and Cursor.

AI-agent-first headless CMS for Astro 6 + Cloudflare

AI agent skills for Contentrain — workflow procedures, framework integration guides

ElasticDash MCP server — search, inspect, and rerun AI agent traces from ElasticDash

TikTok CLI - designed for AI Agent and developers

CLI for tracking AI agent token usage

AI agent with streaming, tool calling, and conversation persistence. Powered by [Strands Agents SDK](https://strandsagents.com/).

Enact Factory — autonomous AI agent orchestrator (Claude, GPT, Codex, local models)

CLI launcher for Agent HQ — task management for AI agent teams

agentto connector — links your locally-installed AI agent CLIs through link.agentto.net to Agent to Dashboard (dash.agentto.net). Run `agentto` for a TUI.

MCP server for iterate — AI agent integration

Provider-neutral stream-json event projection for LLM agent loops

Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold

Code-orchestrated workflows for Elyra -- define multi-step pipelines where code handles control flow and LLMs handle judgment

Generic fork sync & preservation agent powered by @sctg/cline-sdk

General-purpose agent with transport abstraction, state management, and attachment support

Anthropic Claude phase executor for Coro — wraps the Claude Agent SDK and exposes it through the PhaseExecutorRuntime contract.

Explainable backend flows — automatic causal traces, decision evidence, and MCP tool generation for AI agents

LangChain.js tools for Agent402.Tools: turn its catalog - 500+ strong: 400+ x402 pay-per-call tools + 100+ skill packs (browser, web search, OCR, PDFs, memory) - into LangChain tools via four meta-tools (find/route/call/about), plus the cross-seller x402

Atomic Mail LangChain toolkit — register, jmap_request, and help tools for JS/TS agents.

LangChain tools for Microsoft To Do (Microsoft Graph /me/todo) — direct REST calls, no MCP. Extracted from Jarela.

Core package for building agents that interact with the Hedera network.

LangChain.js BaseChatMemory implementation backed by Mnemosyne. Persistent, searchable, container-scoped chat history with hybrid BM25+vector recall. Replaces LangChain's in-process BufferMemory and ZepMemory. Per-conversation thread tracking, automatic r

Content Tools MCP - AI/LangChain/Mastra tools for the CMS service API

[](https://www.npmjs.com/package/@agentclientprotocol/codex-acp)

Framework for building Slack-like teams of AI agents — CLI, API, and web UI.

The moxxy runtime as a programmatic library: the agentic Session + runTurn loop, the event log, the plugin host, every block registry (providers, tools, modes, compactors, cache strategies, channels, …), session persistence, and the permission engine. Pai

Agentic coding harness that makes any AI API (with or without native tool-calling) generate and apply code. OpenRouter, Ollama, and any OpenAI-compatible endpoint.

Interactive AI coding assistant CLI powered by Nuvin core

OpenAI-compatible Chat Completions adapter for host responders.

Madarx OS — Next.js product with SQLite-backed runtime, scheduled cron daemon, and approval-gated local runners.

Interactively scaffold an AI agent skill or plugin (Claude Code plugin, OpenAI Custom GPT Action, OpenClaw, or Google ADK/Gemini) from a single spec.

OpenAI provider for the Browsary pipeline framework

ORCA — an autonomous coding-agent orchestrator with an autopilot overseer, daemon API and web UI. Install globally and run `orca`.

Titan: Pi-based autonomous CLI agent with OpenRouter, memory, browser control, and Visual Learning.

Honcho memory for the Vercel AI SDK -- persistent identity, theory-of-mind, dialectic reasoning

Official Waffo PSP Node.js SDK

TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support

SDK for interacting with Kimi Code CLI

Provider-agnostic multi-agent orchestration MCP server

Multi-agent coordination for AI coding agents - Claude Code, Cursor, and Codex.

Minimal multi-agent pipeline for OpenCode — strategist → architect → engineer → auditor with ponytail lazy-dev ruleset baked in.

Real-time multi-agent coding CLI with shared context, adaptive co-editing, dedicated agent terminals, and headless CI runs.

QECopilot (🥝 KIWI) — AI-Native Multi-Agent Execution Platform for Natural Language Software Testing

Scope audit + multi-agent coordination for AI coding agents. Catches scope creep in diffs and coordinates Claude Code, Cursor, and Codex on the same repo.

spec-manager: SDD workflow layer for AI coding agents. Specs, decisions, tasks, and verification in markdown/JSON. Portable CLI + multi-agent instructions.

Maverick: Fine Terminal Multi-Agent Ecosystem — Shared Vault + CLI

Agent Action Compression Protocol — TypeScript SDK for multi-agent LLM coordination

Web chat interface for NanoClaw AI agent framework

Cloudflare-optimized AI Agent Framework

CLI tool for Nimbus AI Agent Framework

Node.js RSS and Atom feed parser with agentic analysis, LLM enrichment, heuristic deduplication, and Model Context Protocol (MCP) server tooling. Drop-in rss-parser compatible. Zero-dependency hand-rolled XML parser with SSRF protection, pluggable storage

MCP server for Agentic KDD — 60 tools

Credential primitives for the P3 Agentic Registry — types, canonicalization, hashing, and validation

Local architecture context CLI for agentic coding workflows.

Core components and theme for the Agentic Design System — AgenticProvider, Button, CodeBlock

Agentic Version Control System — an AI-native VCS where intent, session, operation, evidence and decision are first-class objects and code is a materialized projection of an operation graph.

Omniboard.dev MCP server that exposes agentic check runs and run progress for local agents.

Command-line client for Sifta Agentic Talent sourcing workflows.

Get Engineering Done: structured agentic workflows for engineering programs

Design tokens for the Agentic Design System — framework-agnostic JS constants and CSS custom properties

Easier to use Agentic Framework for multi-turn LLM flows.

YAAgents TypeScript client — Agentic REST Profile v0.3

Track AI agent costs, tokens, runtime and spending. Prevent runaway OpenAI, Anthropic, LangGraph and OpenRouter agents from exceeding budget.

A terminal-native AI agent for builders

Sign and verify prompt templates and tool definitions for AI agent security