Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Main repository for Datadog Agent

01Result

DataDog/datadog-agent ↗

DataDog/datadog-agent AI coding statistics: 0.5%

of 5,426 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.5% agent · top contributor 36%11 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

25
agent commits
5,401
other considered commits
11
agent contributors
36%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

25assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%725
2026-030.3%794
2026-040.7%845
2026-050.3%668
2026-060.6%708
2026-070.1%670
2026-080.6%691
2026-091.8%325

Peak month: 1.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Other / generic agentVarious140.3%
Claude CodeAnthropic110.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 8777888d on GitHubBuild rshell as a static pure Go binary (#56369)Other / generic agent
  • 638de172 on GitHubprivateactionrunner/rshell: log effective settings at Info level (#56152)Other / generic agent
  • f3570c35 on GitHubprivateactionrunner: fix duplicate action_fqn/task_id log fields (#56148)Other / generic agent
  • 40ffcbf3 on GitHubfix(ci): share a single `orchestrion` job server across e2e binary builds Claude Code
  • ca1ecdfa on GitHubci(e2e): decouple go_e2e_test_binaries build parallelism from CPU request Claude Code
  • 77ad0d23 on GitHubAdd additional approvers to static quality gate EXCEPTION_APPROVERS (#5486Claude Code

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window6,287
Merge commits removed−0
CI / dependency bots removed−861
Considered5,426

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Go AI coding statisticsCompare evidence across Go repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli DataDog/datadog-agent

Scan another repository

Try