All organizations · GSoC 2026 · Science and medicine, Artificial Intelligence

Project Mesa

Mesa: Agent-based modeling in Python 3+

Mesa is an Apache2 licensed agent-based modeling (or ABM) framework in Python. It allows users to quickly create agent-based models using built-in core components (such as spatial grids and agent schedulers) or customized implementations; visualize them using a browser-based interface; and analyze their results using Python’s data analysis tools. Its goal is to provide an ecosystem to support generative science approaches, improve understanding of complex systems and aid practical decision-making.

  • python
  • gis
  • object oriented programming
  • LLMs
  • network topology
  • simulation
  • Agent Based Models
  • Generative Science

Project ideas

3 ideas on its 2026 ideas page; of the 1 that state a difficulty: 1 hard. Sizes: 3 medium. 6 mentors named.

  1. Modernizing Mesa‑Geo: PropertyLayer Refactor, Aggregation API and Visualization Overhaul medium
  2. Mesa LLMs iteration to push to production medium hard
  3. Meta Agents medium

Read the ideas page. Ideas are for scope reference; never copy one into a proposal.

History

In GSoC since 2024, 3 years. Projects per year: '24: 3, '25: 4, '26: 3.

On GitHub

6 repositories pushed to in the last year. Main languages: Python (5).

Links and channels

go deeper in your terminal
git-into-gsoc org "Project Mesa" --shortlist
git-into-gsoc repos "Project Mesa"
git-into-gsoc issues --org "Project Mesa"
or ask your assistant:
"Which Project Mesa repositories merge
newcomers' pull requests, and which beginner
issues are still free?"

Those commands read live data: which repositories merge outside pull requests, and which beginner issues nobody has claimed. Install in two minutes.