MCP Directory
Back

model-compose

by hanyeol · Python · ★ 73

Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.

#agent-framework#ai-agents#ai-infrastructure#ai-workflow#anthropic#declarative#huggingface#langchain-alternative#llm#llm-framework#llm-orchestration#llmops#mcp#mcp-server#model-context-protocol#openai#rag#vector-database#workflow-orchestration#yaml

Install

pip install git+https://github.com/hanyeol/model-compose.git

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "model-compose": {
      "command": "uvx",
      "args": [
        "git+https://github.com/hanyeol/model-compose.git"
      ]
    }
  }
}

From the README

[](https://python.org) [](https://pypi.org/project/model-compose/) [](https://opensource.org/licenses/MIT) [](https://pepy.tech/project/model-compose) [](http://makeapullrequest.com) [한국어](README.ko.md) | [中文](README.zh-cn.md) AI systems should not be locked into a single provider, runtime, or cloud. They should remain portable, inspectable, and able to run anywhere. Today, many AI applications are tightly coupled to provider-specific APIs, managed runtimes, and closed ecosystems. While convenient at first, this coupling introduces vendor lock-in — components can't be swapped without rewrit…
Read full README on GitHub →

Related databases servers