MLE-agent

Python command-line pairing agent for ML engineers that builds baselines, works Kaggle-style tasks and writes weekly reports.

Agent by MLSysOps

IndexedMIT★ 1,574

Write a review

Get started

Setup steps are in the repository. Repository

About

MLE-Agent is a pairing agent for machine learning engineers and researchers. It creates a project, prototypes ML baselines from a stated requirement, and checks code through a coder and debugger loop. It also pulls methods from arXiv and Papers with Code, generates weekly work reports from GitHub or a local git repository, and offers an interactive chat in the terminal.

Use cases: coding, research, code-generation, documentation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: coding, researchREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: mistralREADME
Open source: Yes

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 1,574
Forks: 111
Open issues: 29
Last commit: Jul 10, 2026 (3 months ago)
Last release: Oct 12, 2024 (2 years ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/MLSysOps/MLE-agent
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql