Streaming AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.
Star History
Momentum
+10
STARS · LAST 30 DAYS
1
PER DAY
#738
MOST-STARRED Python
| Window | 7 days | 30 days | 90 days |
|---|---|---|---|
| Stars gained | +7 | +10 | +90 |
| Per day | 1 | 1 | 1 |
| Forks gained | +1 | +3 | +10 |
model-compose gained 10 stars in the last 30 days, about 1 a day, and now has 113. It is about 1 year old and has averaged roughly 113 stars a year. It ranks #738 among Python repositories and #6,453 across all languages on GitHubRepo.
Trending Record
5
DAYS ON TRENDING
#2383
BEST RANK
Sep 24, 2026
FIRST APPEARANCE
Active
STATUS TODAY
model-compose has maintained a continuous presence across global trending indexes, peaking at #2383. Below is the 30-day activity profile:
💡 Overview
model-compose is an open-source project written in Python: Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.
Engineered for speed, consistency, and developer ease, it solves common hurdles in agent-framework, ai-agents, ai-infrastructure. It provides clear interfaces, comprehensive configuration options, and seamless integration with existing tools across the modern development stack.
⚡ Key Features
Optimized execution pipeline written in Python for predictable speed.
Zero-friction configuration with comprehensive sensible defaults out of the box.
Cross-platform runtime support across Linux, macOS, and Windows environments.
Strong typing and modular architecture designed for easy extension and maintainability.
Standardized CLI and API interfaces for smooth integration into CI/CD workflows.
Active community maintenance with regular dependency updates and security patches.
📥 Installation
$ pip install model-compose
⚙ System Requirements
Platforms
- • macOS
- • Linux
- • Windows
Runtime & Dependencies
Python >= 3.9, pip, virtualenv
Architecture
x86_64, ARM64 (Apple Silicon & Graviton)
🧠 How It Works
model-compose coordinates its core functionality through a modular Python pipeline. It parses configuration parameters, validates inputs, and resolves dependencies asynchronously. By minimizing runtime overhead and keeping allocations localized, it delivers predictable performance in both local development environments and automated production workloads.
🎯 Production Use Cases
Autonomous AI Agents
Orchestrate intelligent workflows and tool-calling routines with model-compose.
Model Inference & Prompting
Integrate fast, local or cloud-hosted generative AI models directly into production code.
Context Memory & RAG
Augment language models with dynamic vector retrieval and structured project memory.
Developer Productivity
Automate repetitive engineering tasks, code generation, and test creation using AI agents.
🚀 Getting Started
Install model-compose using your package manager: `pip install model-compose`
Initialize your project workspace or configuration file for model-compose.
Import model-compose into your codebase or invoke it directly from your terminal.
Execute your test suite or run `model-compose --help` to verify successful setup.
👍 Strengths
⚠️ Considerations
⇄ Alternatives & Direct Competitors
👥 Who Should Use This
Developers and engineering teams building with Python, seeking reliable, tested, and actively maintained tooling for production workloads.
🏆 Nearby in the Rankings
hanyeol/model-compose is currently ranked #6,453 by stars across every repository tracked on GitHubRepo. These are adjacent projects:
| Rank | Repository | Language | Stars | Action |
|---|---|---|---|---|
| #6,435 | tsaijamey/frago | Python | ★ 114 | Compare ↗ |
| #6,435 | mickadesign/metadata-gen | JavaScript | ★ 114 | Compare ↗ |
| #6,435 | jarczakpawel/OrcaStudio | C++ | ★ 114 | Compare ↗ |
| #6,435 | marketcalls/openalgo-charts | TypeScript | ★ 114 | Compare ↗ |
| #6,435 | Gen-Verse/JEPA-Anything | Python | ★ 114 | Compare ↗ |
| #6,453 | hanyeol/model-compose This Project | Python | ★ 113 | |
| #6,453 | robmckinnon/rugalytics | Ruby | ★ 113 | Compare ↗ |
| #6,453 | cpjolicoeur/bb-ruby | Ruby | ★ 113 | Compare ↗ |
| #6,453 | tuulos/ringo | Erlang | ★ 113 | Compare ↗ |
| #6,453 | balinterdi/i15r | Ruby | ★ 113 | Compare ↗ |
| #6,453 | lwe/page_title_helper | Ruby | ★ 113 | Compare ↗ |
Frequently Asked Questions
What does model-compose do? +
Streaming AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.
What language is model-compose written in? +
The primary language is Python. Topics include: agentic-ai, ai-agents, ai-orchestration, ai-pipeline, audio-processing.
Is model-compose actively maintained? +
Yes, the last recorded push was on Sep 26, 2026 with 2 open issues being tracked.
How many stars does model-compose have? +
model-compose has 113 stars and 16 forks on GitHub.
How does model-compose rank among GitHub repositories? +
With 113 stars, hanyeol/model-compose is ranked #6,453 globally across all repositories tracked on GitHubRepo and #738 among Python projects.
What license is model-compose distributed under? +
The repository reports a MIT license. Always verify the repository LICENSE file for legal terms.