Agents for robot physical reasoning
active 2026-02-14 → 2026-08-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 186 days from 2026-02-14 to 2026-08-18. Pushes: 158 total, peak 14 in a day. Pull requests: 36 total, peak 13 in a day. Issues: 10 total, peak 5 in a day. Comments: 21 total, peak 9 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 |
|---|---|---|---|---|
| tomsilver | 91 | 42 | 27 | 9 |
| Jaraxxus-Me | 71 | 50 | 6 | 4 |
| merlerm | 52 | 44 | 2 | 3 |
| weiqianwang123 | 17 | 15 | 1 | 0 |
| Copilot | 7 | 0 | 0 | 5 |
| yichao-liang | 7 | 7 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#148merlerm2026-08-18 13:25Support bilevel primitives in blackbox
- Pull request#117merlerm2026-07-08 10:27
- Pull request#97Jaraxxus-Me2026-04-19 18:07
- Issue#96merlerm2026-04-10 16:52Implement anthropic-proxy to run claude code with other API models
- Pull request#92Jaraxxus-Me2026-04-03 18:42
- Pull request#88weiqianwang1232026-03-30 22:46
- Issue comment#72merlerm2026-03-17 14:22Render policy primitive + MCP Tools
- Pull request#71tomsilver2026-03-07 23:43
- Pull request#67merlerm2026-03-01 13:15
- Issue#62Jaraxxus-Me2026-02-25 16:29Idea 3: Ask it to create skills
- Issue#64Jaraxxus-Me2026-02-25 16:27Fix Copying Everything from Sandbox to the Main Approach
- Issue#59Jaraxxus-Me2026-02-25 16:27Run all of the environments and figure out the easiest unsolvable environments
- Issue#61Jaraxxus-Me2026-02-25 16:27Idea 2: Constrained Program Template
- Issue#64Jaraxxus-Me2026-02-25 16:21Fix Copying Everything from Sandbox to the Main Approach
- Issue comment#53merlerm2026-02-25 10:40possibly implement LLM/VLM API call as a primitive
- Pull request#49tomsilver2026-02-24 21:52
- Issue#52tomsilver2026-02-24 13:35change `experiments/analyze_results.py` to average over seeds
- Issue#43tomsilver2026-02-24 10:50ensure that evaluation seeds are non-obvious to prevent memorizing during training
- Pull request#45tomsilver2026-02-23 15:54
- Pull request#42tomsilver2026-02-23 14:42
- Pull request#41tomsilver2026-02-23 14:27
- Issue#40tomsilver2026-02-23 13:39check if red teaming script now works with docker
- Pull request#37Jaraxxus-Me2026-02-22 19:04
- Issue comment#34Jaraxxus-Me2026-02-20 19:18Sandbox docker
- Pull request#34Jaraxxus-Me2026-02-20 01:40
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.