LLM eval framework. Compare any model via OpenAI-compatible API.
active 2026-03-24 → 2026-05-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 63 days from 2026-03-24 to 2026-05-25. Pushes: 152 total, peak 56 in a day. Pull requests: 23 total, peak 8 in a day. Issues: 42 total, peak 29 in a day. Comments: 3 total, peak 3 in a day. Stars: 0 total, peak 0 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 |
|---|---|---|---|---|
| hnshah | 193 | 126 | 23 | 3 |
| bobhns | 21 | 20 | 0 | 0 |
| github-actions[bot] | 6 | 6 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#141hnshah2026-05-24 01:08
- Pull request#127hnshah2026-04-15 02:32
- Pull request#124hnshah2026-04-15 01:00
- Issue#116hnshah2026-04-03 01:42feat: verdict costs — summarize API spend across runs
- Issue#116hnshah2026-04-03 01:42feat: verdict costs — summarize API spend across runs
- Issue#116hnshah2026-04-03 01:42feat: verdict costs — summarize API spend across runs
- Issue#115hnshah2026-04-03 01:41feat: verdict import --hf — import HuggingFace datasets as eval packs
- Pull request#109hnshah2026-04-02 11:26
- Pull request#103hnshah2026-04-02 06:25
- Pull request#101hnshah2026-04-02 05:22
- Pull request#92hnshah2026-04-02 03:08
- Issue#87hnshah2026-04-02 03:07feat(scorer): add `latency` and `cost` threshold scorers
- Pull request#95hnshah2026-04-02 03:04
- Pull request#98hnshah2026-04-02 02:49
- Pull request#94hnshah2026-04-02 02:42
- Pull request#78hnshah2026-03-31 00:07
- Pull request#78hnshah2026-03-31 00:07
- Issue#62bobhns2026-03-30 06:50Dashboard Integration - Files and Coordination
- Issue comment#57hnshah2026-03-29 19:51feat: add cot_classify LLM judge pattern
- Issue comment#56hnshah2026-03-29 19:51Add named eval registry (reference evals by ID, not file path)
- Issue#19hnshah2026-03-29 15:16Add `javascript` custom scorer
- Issue comment#46hnshah2026-03-29 10:18Support JSONL dataset files for large-scale eval cases
- Pull request#54hnshah2026-03-29 07:20
- Pull request#50hnshah2026-03-29 07:19
- Pull request#49hnshah2026-03-29 07:19
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.