Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

langchain-ai/langchain ↗

langchain-ai/langchain AI coding statistics: 1.8%

of 923 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.8% agent · top contributor 29.4%9 contributors
org-wide

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

17
agent commits
906
other considered commits
9
agent contributors
29.4%
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

15assisted
2autonomous

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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%5
2026-022%150
2026-032.6%151
2026-042.4%124
2026-051.1%93
2026-061.4%148
2026-072.6%77
2026-081.4%147
2026-090%28

Peak month: 2.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic141.5%
GitHub CopilotGitHub30.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4717cfc8 on GitHubfeat(openai): support explicit prompt caching (#38762)Claude Code
  • fd822b07 on GitHubfix(text-splitters): restore lazy imports for heavy optional dependencies Claude Code
  • de950252 on GitHubfeat(perplexity): `bind_tools` and Responses-API tool round-trip (#37934)Claude Code
  • 67fa96ff on GitHubdocs(groq): remove duplicate `method` block from `with_structured_output` GitHub Copilot
  • 5650448a on GitHubfeat(core): incorporate gateway metadata to traces (#39703)GitHub Copilot
  • e939c967 on GitHubfix: compaction typo (#35467)GitHub Copilot

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 window1,560
Merge commits removed−0
CI / dependency bots removed−637
Considered923

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
langchain-ai/langchain
Default branch
master
Resolved HEAD
c01de7fed06b83fcc95d1d06e9b67943a7454a2a ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position29th percentile

Midrank percentile; equal shares split the tied positions.

Repository
1.8%
Cohort median
6.3%
Share rank
174 / 247
0th50th100th

Percentile = (repositories below + half of 3 tied repositories) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →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 langchain-ai/langchain

Scan another repository

Try