Evaluation harness for OpenHands V1.
Python · active 2025-10-21 → 2026-08-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 292 days from 2025-10-21 to 2026-08-08. Pushes: 847 total, peak 22 in a day. Pull requests: 214 total, peak 12 in a day. Issues: 143 total, peak 9 in a day. Comments: 1,019 total, peak 31 in a day. Stars: 22 total, peak 2 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 |
|---|---|---|---|---|
| simonrosenberg | 788 | 492 | 82 | 115 |
| github-actions[bot] | 392 | 0 | 0 | 392 |
| juanmichelini | 372 | 143 | 42 | 102 |
| openhands-ai[bot] | 258 | 0 | 0 | 242 |
| xingyaoww | 165 | 100 | 18 | 25 |
| all-hands-bot | 162 | 3 | 0 | 95 |
| neubig | 148 | 71 | 16 | 27 |
| dependabot[bot] | 63 | 20 | 37 | 6 |
| VascoSch92 | 19 | 14 | 2 | 2 |
| enyst | 9 | 2 | 2 | 4 |
| ryanhoangt | 6 | 4 | 0 | 2 |
| MadhaviSG | 5 | 0 | 4 | 0 |
| 18jeffreyma | 5 | 0 | 1 | 3 |
| cizezsy | 3 | 0 | 2 | 0 |
| AmyTao | 3 | 0 | 0 | 3 |
| GaokaiZhang | 2 | 0 | 2 | 0 |
| linear[bot] | 2 | 0 | 0 | 0 |
| SefaZeng | 2 | 0 | 0 | 1 |
| enochii | 2 | 0 | 0 | 1 |
| Rainhunter13 | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue#746neubig2026-06-22 01:49Track PR #745: Add local Apptainer SWE-bench image builds
- Pull request#732dependabot[bot]2026-06-22 00:33
- Issue comment#743all-hands-bot2026-06-15 22:42Add Apptainer SWE-bench evaluation
- Issue comment#743openhands-ai[bot]2026-06-09 21:34Add Apptainer SWE-bench evaluation
- Pull request#740juanmichelini2026-06-06 01:22
- Pull request#732dependabot[bot]2026-06-01 01:18
- Pull request#727neubig2026-05-30 20:47
- Issue comment#727neubig2026-05-30 20:47[codex] Extract shared Harbor benchmark runner
- Issue comment#727neubig2026-05-30 04:36[codex] Extract shared Harbor benchmark runner
- Issue comment#644all-hands-bot2026-05-28 22:05Filter SWE-Bench Multimodal image builds to curated subset
- Issue comment#711juanmichelini2026-05-27 22:42DRAFT: swtbench: strip non-test files from model_patch in post-processing (option 2 of #708)
- Issue comment#716juanmichelini2026-05-26 19:57fix: replace DelegateTool with TaskToolSet (removed in SDK v1.23.0)
- Pull request#714enyst2026-05-24 19:52
- Pull request#714enyst2026-05-24 00:13
- Issue#708juanmichelini2026-05-12 15:04swtbench: qwen3-coder-next score is artificially low — agent writes source-code fix alongside the test (78% of patches)
- Issue#576neubig2026-05-04 21:32Tracking: ACP Agent Full Benchmark Runs
- Issue comment#702simonrosenberg2026-05-01 23:36fix(evaluation): gc.collect() after each instance to reclaim cyclic RemoteConversation objects
- Pull request#701simonrosenberg2026-05-01 15:25
- Issue comment#641AmyTao2026-05-01 02:53feat/add SkillsBench benchmark integration
- Pull request#701simonrosenberg2026-05-01 00:21
- Issue comment#680juanmichelini2026-04-30 01:23DO_NOT_MERGE_FOR_TESTING_ONLY - Simulate eval_infer error
- Pull request#691juanmichelini2026-04-30 01:21
- Issue comment#680juanmichelini2026-04-24 16:47DO_NOT_MERGE_FOR_TESTING_ONLY - Simulate eval_infer error
- Issue comment#684VascoSch922026-04-24 03:17GHCR `eval-agent-server` has 133k+ tags with no retention; tag scheme fans out per SDK sha
- Issue#695simonrosenberg2026-04-23 16:17Investigate: SWE-bench full-500 image build >6h with acp-claude vs ~4.5h standalone — what's different?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 22 stars here means stars gained during the window, not the repo's star count.