npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

splash-agent

v2.5.1

Published

Splash — Autonomous Agent Platform: CLI + multi-provider agent loop + TUI dashboard + platform bots

Readme

   ███████╗██████╗ ██╗      █████╗ ███████╗██╗  ██╗
   ██╔════╝██╔══██╗██║     ██╔══██╗██╔════╝██║  ██║
   ███████╗██████╔╝██║     ███████║███████╗███████║
   ╚════██║██╔═══╝ ██║     ██╔══██║╚════██║██╔══██║
   ███████║██║     ███████╗██║  ██║███████║██║  ██║
   ╚══════╝╚═╝     ╚══════╝╚═╝  ╚═╝╚══════╝╚═╝  ╚═╝

Splash: Agent Engine for Agencies

TypeScript License Build Tests Version

A production-ready, self-improving, multi-provider autonomous agent engine built for reliability, precision, and agency workflows.


⚡ What is Splash?

Splash Core (v3.1.1) is an autonomous execution engine—not a chatbot. It is a strictly contract-based, multi-modal AI system that executes real-world tasks with precision, automatically audits its own work, and evolves its memory layers from every operation. Built for developers and agencies looking for deterministic outcomes over conversational fluff.

🌟 Why Splash?

  • Contract-First Execution: Every multi-step task generates a typed JSON execution contract outlining steps, token budgets, and verification criteria before execution begins.
  • Advanced Memory Architecture: A robust 4-layer memory system (Working, Episodic, Semantic, Procedural) with a dedicated Trash Memory quarantine to prevent adversarial noise from polluting core skills.
  • Safety as a First-Class Concern: Four configurable safety tiers (permissive, standard, strict, paranoid) physically block destructive actions and leakages, validated by independent safety filters.
  • Instant Fast-Paths: Deterministic sub-100ms bypasses for common operations, sidestepping the LLM loop entirely to save tokens and time.
  • Multi-Provider Arbitration: Native routing to OpenRouter, Claude, OpenAI, Gemini, DeepSeek, and local Ollama deployments with automatic rate-limit fallbacks.

📦 Install

You can install Splash with a single curl command on macOS and Linux:

curl -fsSL https://raw.githubusercontent.com/splash-agent/splash/main/scripts/install.sh | bash

For Windows PowerShell and manual installation methods, see docs/INSTALL.md.

Initialize Configuration:

splash init

🚀 Quickstart

Splash natively supports execution directly from the command line:

1. Instant Fast-Path Tasks

# Bypass the LLM entirely for deterministic system commands
splash "list files in src/"

2. Autonomous Agent Loops

# Engages the full contract builder and execution loop
splash "debug the memory leak in packages/core/src/agent-loop.ts"

3. Background Detached Runs

# Detaches execution to the daemon so you can track it later
splash "build a FastAPI todo service" --background

🛠️ Features

Core Engine

  • Contract Builder: Generates deterministic execution plans (packages/core/src/contract-builder.ts).
  • State Machine: Strongly-typed execution lifecycle (packages/core/src/state-machine.ts).
  • Reflector: Evaluates executed steps and extracts permanent learnings, scoring quality via an automated heuristic.

Memory Systems

  • Semantic Memory: Long-term storage of validated facts.
  • Episodic Memory: Context tracking across sessions.
  • Trash Memory: Quarantines failed, noisy, or adversarial prompts to prevent skill pollution.

Skills

  • 36 Built-in foundational skills loaded dynamically via registry.
  • Heavy dependencies dynamically imported to preserve <100ms startup times.

Connectors

  • Real: Filesystem, Webhook, Terminal, Browser, HTTP.
  • Configuration Available / Coming Soon: Gmail, SMS, Telegram, Discord, Slack, WhatsApp. (Note: these gateway connectors currently validate config but await full real-world REST API mappings).

CLI / TUI

  • Fully-featured non-interactive mode.
  • Interactive ink-based Terminal User Interface (splash tui) for real-time state monitoring.

Providers

  • Native API connectors for Anthropic, OpenAI, Google Gemini, Groq, Mistral, Together, DeepSeek, and Ollama.

🗺️ Roadmap

  • Done: V3 Engine (Contract Execution, Memory Layers, Safety Engine, Trash Memory).
  • In Progress: Transitioning simulated gateway connectors (Discord, Telegram, Slack) to real REST/WebSocket API implementations.
  • Planned: Full MCP (Model Context Protocol) plugin integration for cross-agent compatibility.

📚 Documentation

📜 License

MIT License. See LICENSE for details.


Built with precision for the autonomous future.