You're the one in charge of your AI agent. But it doesn't know your limits. Authorize, deny, release and record on every consequential action, as an MCP server. Non-custodial.

React voice control with speech transcription, vocalization, and interruption (STT/TTS/VAD) support.

[](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2FPulse-Software-Corp%2Fpulse-ts-sdk) [![npm

A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS

React specific linting rules for ESLint

Global HTTP/HTTPS proxy configurable using environment variables.

SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.

Windows system tray status indicator for opencode — real-time AI status with desktop notifications

The open agent skills ecosystem

HTTP Agent that keeps socket connections alive between keep-alive requests. Formerly part of mikeal/request, now a standalone module.

Ramda Adjunct is the most popular and most comprehensive set of utilities for use with Ramda, providing a variety of useful, well tested functions with excellent documentation.

the http/https agent used by the npm cli

Embeddable Pulse floating chat agent widget.

Loads environment variables from .env file

A PAC file proxy `http.Agent` implementation for HTTP

Versioned learning module, assessment, entitlement, and reward contracts for the Plasius ecosystem

Extreme ESLint configuration

An AI QA team for Unity games — agent-native, engine-native. Spec-driven testing over the official Unity CLI.

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

A Next.js Dashboard application for real-time monitoring and historical analysis of Playwright test executions, based on playwright-pulse-report. This component provides the UI for visualizing Playwright test results and can be run as a standalone CLI too