#4040th of 80 in Agent platforms
zenml
Python MLOps framework that runs ML and agent pipelines on any backend
- Stars
- 5.6k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
5,327 on 21 Apr 20265,639 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ZenML lets you wrap Python code in steps and pipelines, then run them on configurable infrastructure stacks such as Kubernetes, Kubeflow, SageMaker or Vertex. It containerizes and tracks code and records runs with metrics, logs and metadata. It integrates with MLflow, Weights & Biases, Langfuse and LangGraph, and uses a client-server design with a web dashboard.
Who it is for: ML and AI engineers running pipelines and agents in production
Strengths
- Wraps existing code in a @step; no rewrite of scikit-learn, PyTorch or LangGraph code
- Same pipeline runs across stacks like Kubernetes, Kubeflow, SageMaker and Vertex
- Integrates with MLflow, Weights & Biases and Langfuse instead of replacing them
- Covers classical ML, LLM workflows and agents in one framework
Weaknesses
- Production use needs a separate server plus stack setup
- Replay-based agent evals live in the separate Kitaru project
- Aimed at team MLOps; heavy for single-script experiments
- ZenML Pro is a separate hosted offering; the feature split is not detailed
What it needs
- GPU optional
- Docker + Compose
- Needs Python, Kubernetes (optional), MLflow (optional), Object storage (optional)
- Models: scikit-learn, PyTorch, LangGraph, LlamaIndex, LiteLLM
Quick answers
Is zenml open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run zenml with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does zenml need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |