Skip to content

dr-gareth-roberts/insideLLMs

View on GitHub ↗Related repositories →

insideLLMs is a Python library and CLI for comparing LLM behaviour across models using shared probes and datasets. The harness is deterministic by design, so you can store run artefacts and reliably diff behaviour in CI.

active 2025-05-212026-07-31 (UTC)

Partial coverage11,210 / 11,895 hourly files (94%) · 2 absent upstream · 682 failed, retryable2025-04-022026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
456
Pushes
124
Pull requests
40
Issues
0
Stars
2
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 437 days from 2025-05-21 to 2026-07-31. Pushes: 124 total, peak 15 in a day. Pull requests: 40 total, peak 8 in a day. Issues: 0 total, peak 0 in a day. Comments: 177 total, peak 28 in a day. Stars: 2 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

Recent activity

Latest issues, pull requests and releases

  • Pull request#70dependabot[bot]2026-06-04 03:18
  • Issue comment#67github-actions[bot]2026-06-04 03:17
    chore(deps): bump actions/cache from 4 to 5
  • Issue comment#66bolt-new-by-stackblitz[bot]2026-06-04 03:17
    chore(deps-dev): update sphinx-autobuild requirement from >=2021.3.14 to >=2024.10.3
  • Issue comment#57dependabot[bot]2026-06-01 04:14
    chore(deps): update python-dotenv requirement from >=1.0.0 to >=1.2.2
  • Issue comment#56dependabot[bot]2026-06-01 04:14
    chore(deps): update langgraph requirement from >=0.2.0 to >=1.2.2
  • Issue comment#55augmentcode[bot]2026-05-27 23:18
    chore(deps): update langchain requirement from >=0.3.0 to >=1.3.2
  • Issue comment#49augmentcode[bot]2026-05-27 23:17
    chore(deps): bump lewagon/wait-on-check-action from 1.3.4 to 1.7.0
  • Issue comment#56github-actions[bot]2026-05-27 23:16
    chore(deps): update langgraph requirement from >=0.2.0 to >=1.2.2
  • Pull request#58dependabot[bot]2026-05-27 23:16
  • Pull request#58dependabot[bot]2026-05-27 23:16
  • Pull request#57dependabot[bot]2026-05-27 23:16
  • Issue comment#55github-actions[bot]2026-05-27 23:16
    chore(deps): update langchain requirement from >=0.3.0 to >=1.3.2
  • Issue comment#52github-actions[bot]2026-05-27 23:16
    chore(deps): bump actions/deploy-pages from 4 to 5
  • Pull request#55dependabot[bot]2026-05-27 23:15
  • Pull request#55dependabot[bot]2026-05-27 23:15
  • Pull request#55dependabot[bot]2026-05-27 23:15
  • Pull request#52dependabot[bot]2026-05-27 23:15
  • Pull request#52dependabot[bot]2026-05-27 23:15
  • Issue comment#29Codex2026-05-26 08:23
    Hardening pass: tracking, models, runtime, tests, and docs alignment
  • Issue comment#45Codex2026-05-26 07:37
    chore(deps-dev): update sphinx-autodoc-typehints requirement from >=1.24.0 to >=3.0.1
  • Issue comment#47github-actions[bot]2026-05-23 03:00
    chore(deps): update langchain-openai requirement from >=0.2.0 to >=1.2.2
  • Issue comment#43augmentcode[bot]2026-05-23 02:59
    chore(deps-dev): update furo requirement from >=2023.9.10 to >=2025.12.19
  • Issue comment#45github-actions[bot]2026-05-23 02:58
    chore(deps-dev): update sphinx-autodoc-typehints requirement from >=1.24.0 to >=3.0.1
  • Issue comment#43github-actions[bot]2026-05-23 02:58
    chore(deps-dev): update furo requirement from >=2023.9.10 to >=2025.12.19
  • Issue comment#44augmentcode[bot]2026-05-23 02:58
    chore(deps): bump softprops/action-gh-release from 2 to 3

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.