by hanyeol · MCP Server · ★ 75
한국어 | 中文 model-compose Compose AI Systems, Deploy Anywhere. Build AI agents, RAG pipelines, MCP servers, and multi-model workflows in a single YAML file. Run the same system locally, in containers, or in production without rewriting your stack. Inspired by , model-compose provides a portable runtime for AI systems — combining cloud APIs and local models without vendor lock-in. Documentation · Quick Start · Examples · Contributing Philosophy AI systems should not be locked into a single provider, runtime, or cloud. They should remain portable, inspectable, and able to run anywhere.
| Stars | 75 |
| Forks | 3 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.5990598871985/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-07 |
| Created | 2025-05-01 |
| Platforms | docker, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with model-compose for enhanced workflows:
Explore other popular mcp server tools:
model-compose is Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.. It is categorized as a MCP Server with 75 GitHub stars.
model-compose is primarily written in Python. It covers topics such as agent-framework, ai-agents, ai-infrastructure.
You can find installation instructions and usage details in the model-compose GitHub repository at github.com/hanyeol/model-compose. The project has 75 stars and 3 forks, indicating an active community.
model-compose is released under the MIT license, making it free to use and modify according to the license terms.