Coco AI is a unified search platform that integrates enterprise applications and data (such as Google Workspace, Dropbox, GitHub, etc.), providing cross-platform search and AI-driven team chat functions, aiming to improve work efficiency and collaboration experience.

DeepContext is an MCP server that provides symbol - aware semantic search capabilities for code assistants. By intelligently parsing code structure and semantic relationships, it can accurately locate relevant code snippets in large codebases and improve development efficiency.

An efficient task manager that supports multiple file formats (Markdown, JSON, YAML), provides powerful search, filtering, and organization functions, and is designed to minimize tool confusion and maximize LLM budget efficiency.

DevContext is a powerful AI development context system that provides developers with project-centric continuous context awareness. It includes four memory types: short-term, long-term, situational, and semantic, supports code structure analysis and vector search, and significantly improves development efficiency.

Ticketron (tix) is an intelligent command-line tool that uses large language models (LLMs) to simplify the interaction with JIRA, supporting natural language creation and search for work orders and improving work efficiency.

An MCP server that enables AI assistants to directly search for and analyze Datadog logs, improving the efficiency of troubleshooting and log analysis through natural language queries.

Nabu and Nisaba are research prototype toolkits used to enhance the code understanding and development efficiency of LLM agents. Nabu, as an MCP server, provides code semantic search and structure analysis functions, supporting multiple programming languages; Nisaba provides workspace management capabilities for Claude Code through proxy injection and a TUI interface, helping agents manage context usage autonomously.

OneMCP is a universal MCP protocol aggregator that uniformly manages tools from multiple external MCP servers through a meta-tool architecture. It uses progressive discovery and semantic search technologies to significantly reduce token consumption of LLMs and improve tool discovery efficiency.