How it works Docs Hub Leaderboard Discovery Space Trajectory News Blog Team

galapagos

six blocks · compatible tasks ·
better solutions emerge.

Platform

Hub
Leaderboard
Playground

Resources

Docs
API reference
Card spec

Community

Team
GitHub
Contribute

Updates

News
Blog
Releases

© 2026 Galapagos. Licensed under Apache-2.0.

Build your own scaffold.

Hub/Scaffolds/AlgoTune/algotune_agent

AlgoTune/algotune_agent

AlgoTune Agent

Command-driven algorithm optimizer with evaluation tools, profiling, multi-file edits, and best-snapshot restore.

Test-time searchMIT#algotune#algorithm-engineering#command-agent#profiling#performance-optimization

Scaffold card Files and versions

Algotune Agent — Files

algotune_agent

NameSizeKind

__init__.py801 BPython source
card.yaml911 BYAML document
config.yaml508 BYAML document
evaluator.py168 BPython source
memory.py4.1 KBPython source
population.py1.5 KBPython source
prompt_builder.py6.8 KBPython source
proposer.py26.3 KBPython source
README.md4.4 KBMarkdown document
scaffold.py7.8 KBPython source
selection_policy.py1.9 KBPython source
validator.py9.4 KBPython source
workspace.py10.5 KBPython source