AutoML-Agent
Overview
Open-source multi-agent LLM framework for end-to-end automated machine learning pipelines.
Best For Professions:
AutoML-Agent is an open-source multi-agent framework that uses LLMs to automate the full ML pipeline—from data ingestion to model deployment. Designed for diverse data modalities, it decomposes tasks across specialized agents (e.g. prompt, data, model, operation), with retrieval‑augmented planning and multi-stage verification to ensure robust and deployable model solutions.
AI Agent Store research
What the evidence says about AutoML-Agent
AutoML-Agent is an ICML 2025 research framework and code release for full-pipeline automated machine learning, not a hosted commercial agent product. Specialized LLM agents plan and execute data, model, and deployment work, then use verification stages to select and implement a result.
Last reviewed August 15, 2026
Verified capabilities
- Full-pipeline AutoML planning
The framework accepts a natural-language task and plans work from data retrieval through model deployment.[2]
- Specialized parallel agents
Plans are decomposed into subtasks such as preprocessing and neural-network design that specialized agents execute in parallel.[2]
- Retrieval-augmented planning and verification
The system explores candidate plans and applies multi-stage verification to guide code generation and select successful executions.[2]
Where it fits best
Buying and deployment notes
There is no hosted subscription. The research code is available without a license fee under CC BY-NC 4.0, while users supply compute, model endpoints, API access, and any associated usage costs.[1]
Platforms: Python 3.11, Jupyter notebook, GitHub source code[1]
Deployment: Local or self-hosted research environment, Self-hosted OpenAI-compatible model endpoint, External model API[1]
Important considerations
- The code is licensed CC BY-NC 4.0, which prohibits commercial use.[1]
- The documented reference setup is research-oriented: it recommends Python 3.11, Jupyter, a strictly pinned vLLM 0.4.1 setup for the prompt adapter, and an example launch across four GPUs, or an external OpenAI-compatible model endpoint.[1]
- The project reports experiments over selected benchmark datasets; users remain responsible for validating generated pipelines and deployment artifacts on their own data and infrastructure.[1], [2]
Sources and research method (2)
We record only claims tied to public sources checked by our team or listing workflow. Counts above are derived directly from this profile, not a subjective rating.
- DeepAuto-AI/automl-agent | GitHubGitHub · checked 2026-08-15
- AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLOfficial site · checked 2026-08-15
Autonomy level
83%
Comparisons
Custom Comparisons
Some of the use cases of AutoML-Agent:
- Automating full ML workflows with natural‑language instructions.
- Building end‑to‑end AI models across vision, NLP, tabular, time‑series, graph.
- Leveraging modular agents for data, modeling, deployment orchestration.
- Ensuring plan quality via retrieval‑augmented planning and verification.
Loading Community Opinions...
Pricing model:
Code access:
Popularity level: 64%
Turn this profile into a trust signal
Show prospects that AutoML-Agent has a public place where they can check product details, pricing, ratings, and reviews.
Build confidence
Give buyers a third-party profile to explore.
Reduce hesitation
Put validation beside your strongest CTA.
Earn discovery
Every badge links prospects to your listing.
Choose your style
Preview it, then copy the complete embed code.
Shows buyers where to validate your product, pricing, and reputation.
Plain HTML. No signup, script, or maintenance required.
Describe the job. Get an AI worker you can actually message.
We create the setup, keep it running after your laptop closes, and save its memory. Test in the browser, then add Telegram, WhatsApp, or Slack.
Plans start at $29/month. Cancel anytime.
Hosted agent
OpenClaw or Hermes