New:Introducing Socket Scanning for VS Code Marketplace Extensions.Learn more →
Get Started
l

lksrz

npm

1.33K

total weekly downloads

Packages

Current Co-maintainers

Former Co-maintainers

11 packages

@aicommander/agent

Remote-machine agent for AI Commander — lets Claude, Codex and other AI agents run shell commands and detached long-running jobs, builds, batch work, and GPU/ML training on your server or laptop. No exposed SSH, open ports, or VPN.

aicommander-cli

AI Commander - remote machines for your AI agents. See https://aicommander.dev

@aicommander/mcp

Remote shell and long-running background jobs for AI agents on your own machines, without SSH, open ports or VPN. mcprush.com-claim-aicommander-mcp-a162830dbe729ff10e2ad115

mcp-desktop-pro

Advanced MCP server for intelligent computer use automation and AI agent operator control. Supports mouse and keyboard input, window-relative vision and coordinates, Retina display, and screenshot-based debugging. Designed for AI-driven workflows, app and

@mcpfinder/core

Core library for MCPfinder: multi-registry MCP server sync, ranked discovery, trust signals, and install-config generation for AI agents.

@mcpfinder/server

MCP server discovery tool for AI agents. Searches MCP servers across the Official MCP Registry and Glama so your AI can find, evaluate, and install tools on demand.

@omp-studio/core

OMP Studio core: Grenton .omp zip codec, system.xml parser, dictionary extractor, project indexer, grenton-lua lint and editor language intelligence

@omp-studio/omps

OMP Studio agent (omps): online Grenton editor for Lua scripts in .omp projects, with sync, versioning and local AI agents (Claude, Codex)

shellreflex

Offline natural-language to shell command CLI (coming soon).

tellsh

Offline natural-language (Polish & English) to shell command CLI: tool->intent->slot cascade of tiny linear models + templates for bash/zsh/sh/PowerShell (fish/cmd best effort). No LLM at runtime, no native dependencies (pure JS).

tellsh-model-student

Distilled student model for tellsh (3-layer encoder, int8 weights for tellsh's pure-JS runtime, ~17 MB, no onnxruntime): consulted only when the linear cascade's confidence is below 0.6.