Packages

An MCP-based AI operating system for multi-agent workflows, providing process management, memory systems, and built-in tools for financial analysis, blockchain operations, and research.

Visual management panel for the OpenClaw AI Agent framework with built-in AI assistant featuring tool calling and image recognition. Provides one-click installation, configuration, diagnostics, real-time service monitoring, multi-model management, agent workspaces, memory editing, and log viewing — available as desktop app or web server deployment.

A Python visualization library for debugging computer vision projects using PyTorch. Automatically detects tensor types (RGB images, masks, video, optical flow) and renders appropriate visualizations with a single line of code.

Wrapper tool combining Masscan's high-speed port scanning with Nmap's service fingerprinting. Accepts diverse target formats (domains, IPs, CIDRs, URLs) and outputs domain:port pairs suitable for piping into vulnerability scanners like Nuclei or httpx.

A lightweight Java application framework for building web and CLI applications with annotation-based routing, multiple HTTP server backends (Netty, Tomcat, Undertow), and no-main-method design. Tagged as MCP-compatible but MCP implementation details are undocumented.

MCP server that executes Manim animation scripts and returns rendered videos, enabling AI assistants like Claude to generate mathematical animations through conversational interfaces.

Python application framework for automated network discovery and topology visualization using SNMP, CDP, and LLDP protocols. Discovers devices, interfaces, VLANs, and routing info, then generates network topology diagrams.

Valve's Steam Web API providing access to the Steam gaming platform's data: player profiles, game ownership and playtime, achievements, global stats, game news, item economies (TF2, CS2, Dota 2), Steam Workshop content, app metadata, review data, and the Steam store catalog. Uses a service-oriented interface design (IPlayerService, ISteamUserStats, IEconItems, etc.). This deep evaluation covers advanced endpoints, gotchas, and agent-readiness details not covered in the basic steam-api entry.

An AI-powered multi-agent coordination system that automates tasks across social media platforms (TikTok, Instagram, YouTube, X/Twitter, WhatsApp) — translating user intents into structured task chains for buyer targeting, cross-platform promotions, content transformation, automated messaging, and creator discovery.

Curated directory of approximately 7,260 MCP servers organized into 33 categories, serving as a comprehensive reference for discovering MCP server implementations across the ecosystem.

MCP server that enables Claude Desktop to perform real-time web research via Google search integration and webpage content extraction using Playwright. Provides search, page visiting with content extraction, screenshot capture, and research session tracking.

US federal government REST API (CASE Search API) providing programmatic access to federal district, bankruptcy, and appellate court dockets and documents via the Public Access to Court Electronic Records system.

Open-source data catalog that helps teams discover and manage data assets across an organization. Ships as a single binary and catalogs databases, APIs, message queues, and data pipelines with full-text search, interactive lineage graphs, and metadata management.

Asynchronous enumeration and vulnerability scanner that uses Celery task queues to orchestrate network scanning tools (Nmap, Nikto, Gobuster, sqlmap, etc.). Supports service-aware scanning, job control (pause/resume/cancel), subdomain enumeration, and HTML report generation.

Curated directory of Web3-focused MCP servers organized into six categories: Chain-RPC (blockchain interaction), Trading (DEX/CEX), DeFi (liquidity/yields), Market Data (pricing/analytics), Tool (NFTs/smart contracts), and Social (Discord/Telegram). Also promotes DeMCP, a decentralized MCP network with TEE and blockchain-based security.

Open-source vision-language models (GLM-4.6V, GLM-4.5V, GLM-4.1V-Thinking) for multimodal reasoning including image/video/document understanding, visual function calling, interleaved image-text generation, and GUI agent operations.

Standardized format and CLI for packaging and distributing local MCP servers as .mcpb bundles (zip archives with manifest). Enables one-click installation of MCP servers in desktop apps like Claude, similar to Chrome/VS Code extensions.

Ultra-lightweight personal AI assistant distributed as a single static Go binary with built-in semantic memory (SQLite + sqlite-vec), multi-provider LLM support, chat app integrations (Telegram, Discord, Slack, WhatsApp), scheduled tasks, and multimodal input handling.

An Emacs-native AI assistant for agentic development that uses LLM reasoning to select and execute tools (read/write files, run commands, list files) within the Emacs workflow.

Memory operating system for LLMs and AI agents that unifies store, retrieve, and manage operations for long-term memory, enabling context-aware and personalized interactions with multi-modal support.