Back to directory

AutoGluon Assistant

A multi-agent system that automates end-to-end multimodal machine learning workflows, turning raw data into a trained ML solution with no manual pipeline building, across CLI, Python API, web UI and MCP interfaces.

AutoGluon Assistant

AutoGluon Assistant, also called MLZero, is a multi-agent system that automates end-to-end multimodal machine learning and deep learning workflows, transforming raw multimodal data into a working ML solution without manual intervention.

It supports multiple LLM providers, with AWS Bedrock as the default alongside OpenAI, Anthropic and SageMaker, and can be used from a CLI, a Python API, a web UI or an MCP interface. A chat mode answers machine-learning questions conversationally without running any code. A node-based manager combined with Monte Carlo tree search improves on earlier greedy iterative-refinement approaches to searching over candidate solutions.

It currently runs on Linux only, inside a conda environment.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.