Multi-agent benchmark where 7 Felix Agent SDK role-specialized LLM agents manage a RimWorld colony. Think FLE (Factorio Learning Environment) but for multi-agent coordination under uncertainty.
active 2026-03-21 → 2026-06-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 84 days from 2026-03-21 to 2026-06-12. Pushes: 43 total, peak 7 in a day. Pull requests: 6 total, peak 2 in a day. Issues: 12 total, peak 4 in a day. Comments: 14 total, peak 5 in a day. Stars: 1 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| jkbennitt | 70 | 41 | 6 | 12 |
| CalebisGross | 3 | 0 | 0 | 2 |
| github-actions[bot] | 2 | 2 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#32jkbennitt2026-06-10 20:32
- Issue#26jkbennitt2026-06-10 01:40MAP_SUMMARY recomputes colony center per tick — shelter site chases the builders (10 blueprints, 0 shelters)
- Pull request#23jkbennitt2026-06-10 00:33
- Pull request#21jkbennitt2026-06-09 23:48
- Pull request#19jkbennitt2026-05-16 06:36
- Pull request#18jkbennitt2026-04-13 04:18
- Issue comment#7jkbennitt2026-04-13 00:02Create benchmark save files for all 6 scenarios
- Issue comment#13jkbennitt2026-04-12 19:11HeadlessRim Docker: real automated benchmarks + leaderboard infrastructure
- Issue comment#16jkbennitt2026-04-12 18:14Wire #13 infrastructure into game loop + Docker e2e
- Pull request#16jkbennitt2026-04-12 06:13
- Issue#13jkbennitt2026-04-10 05:08HeadlessRim Docker: real automated benchmarks + leaderboard infrastructure
- Issue comment#15CalebisGross2026-04-09 22:25HeadlessRim Docker + real benchmarks + leaderboard infrastructure (#13)
- Issue#11jkbennitt2026-04-07 01:00First-run setup: RIMAPI integration gaps and setup friction
- Issue comment#11jkbennitt2026-04-07 01:00First-run setup: RIMAPI integration gaps and setup friction
- Issue#12CalebisGross2026-04-01 04:23RIMAPI: expose AlertsReadout and LearningReadout via API
- Issue#6jkbennitt2026-03-31 04:55Agents must beat unmanaged baseline
- Issue comment#10jkbennitt2026-03-31 04:23Add MapAnalyst agent + spatial awareness + bootstrap playbook
- Issue comment#10jkbennitt2026-03-31 03:05Add MapAnalyst agent + spatial awareness + bootstrap playbook
- Issue comment#10jkbennitt2026-03-31 01:47Add MapAnalyst agent + spatial awareness + bootstrap playbook
- Issue comment#6jkbennitt2026-03-26 02:35Agents must beat unmanaged baseline
- Issue#7jkbennitt2026-03-25 20:28Create benchmark save files for all 6 scenarios
- Issue#5jkbennitt2026-03-22 00:41Fix agent action failures from live game testing
- Issue#5jkbennitt2026-03-22 00:16Fix agent action failures from live game testing
- Issue comment#3jkbennitt2026-03-21 22:38Local LLM model selection for RLE agents
- Issue comment#3jkbennitt2026-03-21 22:02Local LLM model selection for RLE agents
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.