Supercharge Your LLM Application Evaluations 🚀
Python · active 2025-11-26 → 2026-08-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 257 days from 2025-11-26 to 2026-08-09. Pushes: 44 total, peak 4 in a day. Pull requests: 80 total, peak 7 in a day. Issues: 85 total, peak 18 in a day. Comments: 120 total, peak 10 in a day. Stars: 650 total, peak 23 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 |
|---|---|---|---|---|
| anistark | 163 | 42 | 32 | 42 |
| github-actions[bot] | 25 | 0 | 0 | 22 |
| cgaswin | 14 | 0 | 3 | 7 |
| sanjeed5 | 12 | 0 | 10 | 2 |
| a5512167086 | 6 | 0 | 0 | 1 |
| narabi | 5 | 0 | 1 | 3 |
| vishvaRam | 4 | 0 | 0 | 1 |
| tangjieaaa | 4 | 0 | 0 | 4 |
| MinseongS | 4 | 0 | 1 | 3 |
| jjmachan | 3 | 2 | 0 | 0 |
| munnasuprathik | 3 | 0 | 3 | 0 |
| Raditya0902 | 3 | 0 | 3 | 0 |
| yttrium400 | 3 | 0 | 3 | 0 |
| NickBear-star | 3 | 0 | 0 | 2 |
| dan-vine | 3 | 0 | 0 | 1 |
| florind | 3 | 0 | 0 | 0 |
| Farahala | 3 | 0 | 0 | 3 |
| prabin4 | 3 | 0 | 0 | 1 |
| arielfaur | 2 | 0 | 0 | 1 |
| jacksonjack | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#2922Tanisha-Katara2026-08-06 15:20
- Issue comment#2846Harsh23Kashyap2026-07-13 04:27feat(backends): validate dataset / experiment names on BaseBackend before they reach storage
- Issue#2819ysys1432026-07-07 02:35Proposal: white-box uncertainty (self-FV) confidence for open-weight LLM judges — interested as an example?
- Pull request#2758connerlambden2026-06-05 04:31
- Issue comment#2751aashishkumar-tech2026-06-01 00:27RAGAS telemetry DNS resolution failure can severely slow down evaluations
- Pull request#2756aashishkumar-tech2026-06-01 00:24
- Issue comment#2742github-actions[bot]2026-05-25 05:41feat: split PydanticPrompt into cacheable prefix + variable suffix for implicit caching
- Issue comment#2739github-actions[bot]2026-05-23 13:56Replace deprecated VertexAI classes and add langchain-google-genai dependency
- Issue comment#2727SeCuReDmE-main-dev2026-05-17 03:47RFC: Neutrosophic Evidence Triplet for RAG evaluation
- Issue comment#2727SeCuReDmE-main-dev2026-05-17 01:17RFC: Neutrosophic Evidence Triplet for RAG evaluation
- Issue comment#2728github-actions[bot]2026-05-17 01:16feat: add evidence triplet score metric
- Pull request#2723munnasuprathik2026-05-14 23:24
- Pull request#2722munnasuprathik2026-05-14 23:14
- Pull request#2721munnasuprathik2026-05-14 22:37
- Pull request#2720qizwiz2026-05-14 05:27
- Pull request#2713apurrrva2026-05-12 03:12
- Issue#2708Samia35-29732026-05-11 19:25`InstructorLLM._map_openai_params()` fails to remap `max_tokens` for OpenAI models with dotted versions
- Pull request#2707Raditya09022026-05-10 22:23
- Pull request#2706Raditya09022026-05-10 22:14
- Pull request#2705Vivek767602026-05-10 15:25
- Pull request#2703Raditya09022026-05-10 14:30
- Issue comment#2072mgorjis2026-05-09 23:05RAG using OLLAMA model evaluation with RAGAS
- Pull request#2702Spectual2026-05-09 05:55
- Issue comment#2699Uygniqoar2026-05-08 08:14FactualCorrectness recall mode always returns 0.0 - wrong tp variable used
- Issue comment#2658bongho2026-05-05 01:03feat: make diskcache an optional dependency
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 650 stars here means stars gained during the window, not the repo's star count.