BigHugger
GH Repository · WecoAI

aideml

AIDE: an LLM agent for machine learning engineering — the research Weco grew out of. Referenced in OpenAI MLE-bench.

stars
1,529
30-day movement
+72/day
Related entries
60
Connections
1
pythonllmdata-sciencecode-optimizationmakedockerai-agentsautomated-machine-learningmachine-learningautonomous-agentsaiself-improving-aiautoresearchPythonagent-app

AIDE is an LLM agent for machine learning engineering from Weco AI, described as the research project the company grew out of. It is a Python repository with a Docker-based toolchain and an MIT licence, and it is referenced in OpenAI's MLE-bench.

Reach for it when you want an autonomous agent that automates machine learning engineering work rather than writing every experiment yourself.

Use it to

  • Run automated machine learning engineering tasks
  • Explore self-improving AI and autoresearch workflows
  • Optimize code for ML experiments
  • Reproduce or build on MLE-bench-referenced research

For ML engineers and researchers exploring autonomous agents

Role
agent-app
Language
Python
Licence
MIT
Forks
227
Open issues
2
Last push
2026-09-03
Latest release
v0.1.2 · 2024-04-26
topicsllm-agentsmachine-learningautomated-machine-learningautoresearchcode-optimizationdata-science