Javascript agents

Intercept Kitty Graphics Protocol images from CLI output and inject them into LLM context. A spec and OpenCode plugin for agent-CLI image passing.

Embedded agent simulation & evaluation framework for Node.js/TypeScript

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

🔍 Blast radius & caller analysis for legacy Java. Heuristic-ranked impact audit — npm-installable agent skill for OpenCode, Codex, Claude Code, Copilot, Gemini & DeepCode.

## Table of Contents

Browser-safe agent runtime for the next-generation Cline SDK

Secure multi-platform AI skill installer — scan before you install

N8N node to connect to WatsonX

Playwright Tools for MCP

MCP server for AI coding agent terminal-to-terminal communication. Local-first, SQLite-backed, webhook-integrated.

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

ps adk adapter

Tiny, fast, provider-agnostic LLM agent framework (orchestrator, fallback, race, rate limits, retries, streaming, cost, middleware).

Detect agentic coding environments and AI assistant tools

MoltNet agent runtime — coding-agent-agnostic Task execution loop

Elastic APM JavaScript agent

Local-first project memory for AI coding agents.

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

Maps proxy protocols to `http.Agent` implementations

Native CLI binary for @anthropic-ai/claude-agent-sdk on linux-x64

Efficient, configurable text chunking utility for LLM vectorization. Returns rich chunk metadata.

Context-aware project scaffolding for AI coding agents (Claude Code + Ollama).

Agent Model Layer — One-line LLM access with built-in memory. 29 providers, 18 embeddings, zero lock-in.

Synapse - A Multi Agent Orchestrator

Embeddable TypeScript agent SDK for DeepSeek — built-in tools, skills, memory, and MCP.

SOTA NPM module for agentic processes using local or cloud LLMs.

Package to connect and trace LLM calls.

Vendor-neutral CLI for validating portable Agent Skills

Drop any chat export — WhatsApp, Telegram, Facebook Messenger, more — into your S16 Brain. Run any Brain agent locally with your own LLM (Groq, OpenAI, Ollama, etc.).

A specification compliant robots.txt parser with wildcard (*) matching support.

Agentic visual regression for BlazeDiff. Auto-discovers routes, captures deterministic screenshots, runs CI checks.

A transparent, lightweight LLM agent framework

Raindrop observability for Pi Agent — automatic tracing via subscriber or pi-coding-agent extension

Browser automation tool for pi — interactive browsing, screenshots with inline vision, and session cleanup via agent-browser CLI

The best library to work with LLMs

KC Agent — LLM document verification agent (pure Node.js CLI). Dual-licensed: PolyForm Noncommercial 1.0.0 for personal/noncommercial use; commercial license required for enterprise production. See LICENSE and LICENSE-COMMERCIAL.md.

Secure TypeScript Code Mode for TanStack AI agents to execute sandboxed tool orchestration programs.

CLI for llmist - run LLM agents from the command line

AI SDK v7 provider for Claude via Claude Agent SDK (use Pro/Max subscription)

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

CLI helpers for logging hardware UUIDs and posting startup payloads to Optimus Security.

Bot in a Box — framework for building multi-agent bots

Adaptive LLM router with tier-based model selection and fallback support.

AI-powered browser agent that tests websites like a real user and produces evidence-based, scored reports.

CLI helpers for logging hardware UUIDs and posting startup payloads to Optimus Security.

MCP server for the 1claw secrets vault — lets AI agents fetch, store, and manage secrets at runtime

Agent evaluation framework — prove whether agent changes improved outcomes with reproducible evidence.

SEVO — Automated software delivery pipeline for AI agents (Specify → Execute → Verify → Operate)

Microsoft 365 Activity Protocol adapter for @cuylabs/agent-core turn sources

Fake LLM adapter for Flink AI framework - perfect for demos and testing

Terminal AI coding CLI. Speaks any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates, persistent inpu

Fully featured SOCKS proxy client supporting SOCKSv4, SOCKSv4a, and SOCKSv5. Includes Bind and Associate functionality.

New Relic Browser Agent

ReportPortal client for Node.js

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

Unified LLM API for Anthropic, OpenAI, Google, and DeepSeek. Streaming, retry/backoff, structured output, token normalization. © Diabolical Labs

`AgentFn` adapter that calls an OpenAI-compatible `POST /chat/completions` endpoint using `LlmProvider` from `@uncaged/workflow-runtime`.

最小化 Agent 系统 —— 10 工具 + 插件系统 + workflow DSL + 自动压缩 + OpenAI 兼容 + Ink TUI；NodeNext + tsc 原地编译，dev 用 Bun .ts、install 用 Node .js（学习/教学用）

Open source cost intelligence proxy for AI agents. Cut LLM costs ~80% with smart model routing. Dashboard, policy engine, 11 providers. MIT licensed.

CLI tool for running Netlify agents

CLI entry point for AgentV

[](https://dl.circleci.com/status-badge/redirect/gh/taneliang/coerce-llm-output/tree/main) [![codecov](https://codecov.io/github/taneliang/coerce-l

NebulaOS LLM Gateway provider - OpenAI-compatible chat completions

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

A javascript port of Matomo device-detector

SDK for pyx-memory — Memory as a Service for AI agents

Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system

OpenCode tmux integration: automatically opens subagent panes and renders real-time agent execution with smart layouts

Wiring-engine-driven adaptive reasoning engine with declarative, versioned, hot-reloadable artifact configuration

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

A home for your AI agents

OpenAI-compatible proxy for Cursor CLI — use Cursor models from any LLM client on localhost

Control Nest Thermostats via Google Device Access API. Works with any LLM/agent.

This package provides Spectral-compatible bindings for [@stoplight/json-ref-resolver](https://github.com/stoplightio/json-ref-resolver) and [@stoplight/json-ref-readers](https://github.com/stoplightio/json-ref-readers).

APX — unified CLI + daemon for the Agent Project Context (APC) standard.

JWT-authenticated credential proxy for upstream LLM providers

SkVM — compile and run LLM agent skills across heterogeneous models and harnesses

The agent orchestration layer for Index Network. Implements LangGraph-based workflows for intent processing, opportunity discovery, and chat — decoupled from any specific infrastructure via adapter injection.

Deploy research-driven AI coding assistant assets (skills, agents, commands) into your projects

Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.

First-party OpenInference-shaped tracing for TypeScript LLM and agent applications on Catalyst by Inference.net.

Agent-native LLM Wiki — AI-maintained knowledge base with Obsidian compatibility

Agent-native LLM Wiki — AI-maintained knowledge base with Obsidian compatibility

Zero-dependency (req,res) handler callback agent for use in client requests

MCPLab - Test and evaluate MCP servers with LLMs — run evals, compare agents and launch the MCPLab web app

A lightweight Node.js wrapper for routing HTTP(S) traffic through Tor, including optional ControlPort circuit rotation.

Faceted Prompting — structured prompt composition for LLMs

XAgent Skill Agent Plugin installer for Claude Code, OpenClaw-style agents, Cursor, and generic skill runtimes.

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

Headless spreadsheet formula engine for Node.js services and agents with WorkPaper JSON persistence and formula readback.

CLI tool for CodeLoop — automated verification for AI coding agents

OpenCode TUI sidebar plugin that shows running background sub-agents.

better fetch for Node.js. Works on any JavaScript runtime!

Agent Identity: UserPool (用户池) login, TIP token (工作负载令牌), credential hosting (凭据托管 OAuth2/API key), optional tool/skill permission control (CheckPermission) and risk approval. Integrates with Volcengine 智能体身份和权限管理平台.

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

Self-hosted agent OS with persistent memory, multi-channel presence, tools, scheduling, and sub-agent orchestration

MCP server for controlling the browser via Page Agent extension

Generate LLM-friendly llms.txt files from markdown and MDX content files

Bento Guard SDK - AI-powered security infrastructure for autonomous agents

AWS SDK for JavaScript Bedrock Agent Runtime Client for Node.js, Browser and React Native