Skip to content

AgentOps Toolkit is an open source framework and CLI for adding continuous evaluation and observability to enterprise AI agents. It standardizes evaluation patterns, automates assessments in CI/CD workflows, and generates structured signals that help teams monitor, control, and safely operate agentic systems at scale.

active 2026-04-152026-08-09 (UTC)

Partial coverage11,692 / 12,932 hourly files (90%) · 2 absent upstream · 1,236 failed, retryable2025-02-182026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
422
Pushes
246
Pull requests
14
Issues
13
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 117 days from 2026-04-15 to 2026-08-09. Pushes: 246 total, peak 38 in a day. Pull requests: 14 total, peak 7 in a day. Issues: 13 total, peak 4 in a day. Comments: 5 total, peak 2 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

ContributorContributionsPushesPRsComments
placerda215193112
github-actions[bot]292900
Dongbumlee282013
dependabot[bot]6420

Recent activity

Latest issues, pull requests and releases

  • Issue#396placerda2026-08-07 21:12
    docs(cicd): explain why the generated safety-eval job has no environment
  • Pull request#392placerda2026-08-07 21:08
  • Pull request#384placerda2026-08-07 14:46
  • Issue#343placerda2026-07-01 22:06
    Ship Azure Monitor dashboard for Foundry / Azure OpenAI operational metrics
  • Issue comment#151placerda2026-06-12 20:53
    AI-assisted evaluators fail with HTTP 400 when judge deployment is a reasoning model (gpt-5.x, o1, o3, o4)
  • Pull request#237placerda2026-06-04 20:42
  • Pull request#208placerda2026-05-29 15:31
  • Pull request#204placerda2026-05-29 08:19
  • Pull request#194placerda2026-05-29 03:44
  • Pull request#194placerda2026-05-29 03:44
  • Pull request#191placerda2026-05-29 02:26
  • Pull request#190placerda2026-05-29 02:18
  • Pull request#190placerda2026-05-29 02:17
  • Pull request#186Dongbumlee2026-05-28 20:58
  • Pull request#166dependabot[bot]2026-05-15 15:48
  • Pull request#165dependabot[bot]2026-05-15 15:48
  • Issue#88placerda2026-05-08 16:06
    test: validate eval traces in Azure Monitor (App Insights + GenAI blade)
  • Issue#138placerda2026-05-08 15:59
    Plan AgentOps landing
  • Issue#126placerda2026-05-08 15:57
    Validate tutorial: model-direct evaluation
  • Issue#117Dongbumlee2026-04-29 21:49
    agent_workflow_baseline silently scores ~0 against tool-less agents
  • Issue#116Dongbumlee2026-04-29 21:49
    Default avg_latency_seconds threshold (10s) is unrealistic for Foundry cloud eval
  • Issue comment#115Dongbumlee2026-04-29 21:49
    Implement or hide 'agentops config validate' (currently a stub)
  • Issue comment#115Dongbumlee2026-04-29 21:25
    Implement or hide 'agentops config validate' (currently a stub)
  • Issue#114Dongbumlee2026-04-29 21:18
    results.json schema_version is missing/None
  • Issue#116Dongbumlee2026-04-29 21:18
    Default avg_latency_seconds threshold (10s) is unrealistic for Foundry cloud eval

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.