Deploy apps, sites, WordPress and databases on Hostingsurge; read logs, add domains, migrate sites.
Official CLI for Tein AI models (Video, Image, Audio, LLM, 3D)
The BRAINLLM runtime for the Rust-built web compiler for LLMs: dependency-free ES modules (signals, DOM, router, data, forms, channels). The brain binary embeds this same version.
A local-first project organization for AI assistants: goal-directed processes, project memory and governed learning
Pi model provider for Grok Build: Grok keeps its native harness and tools while Pi drives the session over a local stdio ACP child
Personal AI assistant powered by Pi, Antigravity, Claude, Codex, Codex App, Cursor, Grok, Kiro, OpenCode, and Copilot — Web, Terminal, Slack, Telegram, and Discord interfaces with 33 skills active by
Typed, protocol-neutral application capabilities for Pracht: defineCapability with JSON Schema validation, effect classes, and explicit exposure.
OpenTelemetry instrumentation for MCP servers
Validate VAST 2.0–4.4, VMAP 1.0, and DAAST 1.0 ad tags against IAB specs. 246 rules. Rust/WASM core.
Model Context Protocol server for documonster — lets AI assistants read, write and convert Excel, Word, PDF, CSV and ZIP documents.
Context & memory engineering for AI agents — a markdown-backed, local-first storage engine (substrates, agent memory, progressive disclosure). Your backlog is your agent's memory.
Play a tabletop role-playing game with an AI as your game master: the AI tells the story; RPG Engine remembers the world, rolls the dice and keeps the accounts.
MM3, make and model for coding agents: MAK³ uses what is proven, MDL³ learns what is missing, with compact yes/no checklists, a calibrated consensus, and a log that learns where agents go wrong.
MCP server for continuous repository discoverability monitoring: npm search score, GitHub visibility signals, llms.txt freshness and site checks. Read-only by default.
Agent-native CLI on top of the Expo CLI family
Official JavaScript/TypeScript SDK for the Speech Revolutions speech-to-text API
Hosts, metrics, Docker and authorized_keys over a macOS terminal's live SSH connections
Enterprise-grade MCP server for live docs, best practices, code audit. Context7 alternative — 793+ libraries, evidence-verified answers (never generic), smart dispatch (use gt mcp), plain-text intent
Deploy & release tracking with native MCP — ask Claude what's in production and cut the release.
Session-bound Docker workflow server through Codex. State is discarded with the container.
Deploy, roll back, read logs and manage apps, databases and backups on your self-hosted Tugport.
Deploy Dockerized apps to Akash devnet with ShipDapp MCP build, deploy, update, and logs tools.
Kōbō — local multi-workspace orchestrator for Claude Code and OpenAI Codex, with isolated Git worktrees, live review and optional automation.
Managed deployments on your own Hetzner servers.
Dokploy MCP server: manage apps, Docker Compose, databases, domains, backups, and servers.
An MCP server that provides DevOps and DevSecOps context for the project
Read-only MCP server for self-hosted Atlassian Bamboo CI/CD
Shared machinery for the Apple-app MCP servers: the osascript boundary, TCC-aware errors, and read-only SQLite access
MCP server that maintains structured, two-perspective (internal/usage) code documentation so LLMs read summaries instead of whole codebases.
Model Context Protocol (MCP) server exposing interstellar-tools orbital mechanics, geodesy and map projection calculations and celestial body datasets to AI assistants.
Pi extension: run the mcp-combiner MCP aggregator via sharedserver and inject its tool-discovery directive. Pairs with pi-mcp-adapter, which makes the combiner's tools reachable from Pi.
Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.
Install Relay for Claude Code, Cowork, and Codex, then sign in from the Relay pill.
Command line client for Levelrail, a self-hosted deployment platform
40-tool MCP server for ComfyUI: image generation, ControlNet, IP-Adapter, inpainting, TTS voice cloning, lip-sync video, and AnimateDiff — with smart prompt optimization across 6 model families (Flux,
完整目錄
CI、部署、容器與 Kubernetes。共 5,616 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。