HiveChat is an AI chat application designed for small and medium - sized teams. It supports multiple large - model service providers and provides functions such as group management, Token limits, and third - party login.

TokenScope is a token-aware directory exploration tool for large language models, providing intelligent directory structure analysis, token-aware file content extraction, token usage statistics, and comprehensive report generation functions.

Agent Farm v3.4 is a system based on AI agent evolution and parallel task execution, which realizes task processing through tool - enhanced agents. The new version introduces the chunked write mode, supports the parallel generation of large documents and code files, improves performance by 8.6 times, and uses local models for result synthesis without relying on cloud tokens.

The RLM MCP Server is a large-scale context processing tool based on the Recursive Language Model pattern. It allows Claude Code to process text of over 10 million tokens through external variables, avoiding directly inputting massive content into the prompt. Through the processes of loading, chunking, sub-querying, and aggregation, it supports automatic analysis and programmatic execution, and can connect to the Claude API or the local Ollama for free inference.

repo-to-txt-mcp is a server based on the MCP protocol that converts GitHub repositories or local folders into structured text files, facilitating the provision of context information for large language models. It supports file filtering, token management, and can be integrated with the Cursor editor.

One API is an open-source project that provides a unified access interface to various large models through the standard OpenAI API format. It supports multiple large models and third-party proxy services, and has functions such as load balancing, token management, and user grouping. It is suitable for various deployment scenarios.

This project implements a CRM - AI service middle layer based on the MCP protocol, providing data security processing, intelligent conversation management, and lead analysis functions. It protects sensitive data through anonymization technology and a token system, and supports integration with large - language models.

An MCP server based on the recursive language model pattern, which processes ultra - large - scale contexts (over 10 million tokens) through chunking, sub - queries, and local inference, supporting automatic analysis, code execution, and security filtering.

Code2Prompt is a tool for converting codebases into structured prompts, supporting automatic code processing, intelligent filtering, template customization, token tracking, and Git integration, facilitating interaction with large language models.