hanyeol / model-compose
Declarative 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.
Why this job: topics: ai-orchestration, llm-agents, ai-agents, agentic-ai
What it does
- Any model, anywhere. HuggingFace, vLLM, llama.cpp locally, or OpenAI/Anthropic/Google/xAI via HTTP
- Agents in YAML. ReAct loops, tool use, multi-step reasoning — no code
- Human-in-the-loop. pause workflows for approval, resume from CLI/UI/API
- 100+ components. models, agents, HTTP/WebSocket clients, vector/graph stores, shell, browsers, and more
- Any protocol. HTTP REST, WebSocket, or MCP with one line
Get started
uv pip install model-compose- Maintenance
- Active
- Last commit today
- Stars
- 119
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.4.0
- Released 14 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 94% closed
- 4 still open
- Pull requests
- 22 merged
- 5 waiting
- Releases
- 4
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| receptron / graphai | 374 | 10 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- ai-agents
- declarative
- huggingface
- rag
- agentic-ai
- ai-orchestration
- ai-pipeline
- audio-processing
- ffmpeg
- llm-agents
- local-llm
- mcp-servers
Project record
- JobAgent frameworks
- StatusListed
- Commits2,680
- Forks18
- Watching1
- Stars in 28 days+2
- CreatedMay 1, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026