Packages

Automates a daily AI-related news research pipeline using the Claude Code CLI in headless mode. It performs web searches across multiple topics, compiles a two-tier briefing (TL;DR + full report), publishes the result as a page in a Notion database via Notion MCP, and optionally sends a formatted summary card to Microsoft Teams and/or Slack via webhook(s).

Cordys CRM is an open-source, self-hosted CRM system that manages the full sales lifecycle (leads to cash) including accounts/contacts, opportunities, contracts, and payments/collection workflows. It also advertises integration points (open API/standard interfaces, BI via DataEase) and AI/agent enablement via a “CRM Skills” interface.

ddev-dbserver is part of the ddev ecosystem and is used to run/manage a local database server for development environments (typically via ddev).

devpi-server is a self-hosted Python package index and build coordination server (part of devpi) that provides package upload, indexing, and environment/workflow features for managing Python package releases (including multiple indexes and stages).

Provides an MCP server that accepts PowerShell scripts as strings, executes them, and returns the execution output to the caller/agent in real time.

An MCP (Model Context Protocol) server intended to expose Bitcoin-related capabilities to AI agents via MCP tools (e.g., querying Bitcoin data).

mcp-server-chart is an MCP server package intended to expose charting-related capabilities to AI agents via the Model Context Protocol (MCP). Without repository/README/package-manifest contents, the specific tools, inputs/outputs, and supported chart formats cannot be verified.

Provides MCP (Model Context Protocol) server configurations intended to integrate an agent host with OpenAI (o1 preview) and a Flux image model via separate MCP servers, configured through environment variables and a simple example client config.

mTarsier is an open-source desktop/CLI app for managing MCP servers and connecting them to multiple AI clients (e.g., Claude Desktop, Cursor, VS Code) by reading/editing client MCP configuration files, offering a dashboard/marketplace, and performing config backups/rollback.

Provides an MCP (Model Context Protocol) server interface to interact with a TiDB/TiDB-compatible database, exposing database operations as MCP tools for agent workflows.

A MCP (Model Context Protocol) server intended to integrate timesheet functionality into AI agents, likely enabling the agent to read and/or manage timesheet entries via MCP tools.

Provides an MCP-based server (and associated client CLI) for searching, retrieving, analyzing, and exporting arXiv paper metadata and related citation/trend insights in multiple formats (e.g., BibTeX/RIS/JSON/CSV/YAML), with a REST API and a web UI described in the README.

awesome-openclaw-agents is a curated collection of copy-paste ready OpenClaw agent templates (SOUL.md configurations) plus a quickstart and machine-readable agent listing (agents.json). It also references an MCP servers section and an external deployment/creation flow via CrewClaw, but the provided README content does not include concrete API/MCP technical specifications for the repository itself.

beets is a music library manager that organizes audio files and music metadata. It can scan/import local music, fetch and normalize metadata (artist/album/track info), rename and move files into a consistent directory structure, and maintain an indexed library for searching and further processing via commands and plugins.

A Go SDK implementing the Model Context Protocol (MCP), providing building blocks to create MCP servers (tool/resource/prompt registration and execution) and to communicate with MCP clients over multiple transports (stdio, SSE, WebSocket).

MCPHammer is a Python-based Model Context Protocol (MCP) server (FastMCP over HTTP) that exposes multiple MCP tools, including an Anthropic/Claude query tool, local file execution, URL-based download-and-execute, server info/health endpoints, and configurable “injection” text plus remote management via a separate configuration server. It also supports session logging and a web UI for managing instances and updating configuration (e.g., injection text and init URL).

mcp.science is an MCP server package intended to expose “science” related tools/data to an AI agent via the Model Context Protocol (MCP). Specific tool capabilities, endpoints, and behavior are not provided in the prompt content, so the evaluation is based only on the package name/declared MCP nature.

nginx is a high-performance web server and reverse proxy for HTTP/HTTPS traffic, supporting load balancing, caching, TLS termination, and flexible request routing via configuration.

nginx-static-file-server provides a lightweight way to serve static files using Nginx, typically via a containerized Nginx setup and configuration to map URLs/paths to a static content directory.

OpenManus-RL is a Python-based RL tuning/finetuning codebase for agentic LLM systems, paired with an OpenManus-RL dataset of agent trajectories. It positions Verl (Volcano Engine Reinforcement Learning) as the primary RL training framework (e.g., PPO/DPO/custom reward modeling) and includes environment setup scripts for benchmarks such as WebShop and ALFWorld.