← the index
langchain-ai/langchain
2%
of 896 commits were committed by an AI agent — a floor, not an estimate
2% agent · top contributor 27.8%10 contributors
org-wide

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

18
agent commits
878
human commits
10
agent contributors
27.8%
largest contributor

Assisted or autonomous

16assisted
2autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

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

Which agents

Claude CodeAnthropic151.7%
GitHub CopilotGitHub30.3%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • c253f54bfix(openai): correct `reasoning_effort_levels` for gpt-5 and gpt-5.1 profiClaude Code
  • 4717cfc8feat(openai): support explicit prompt caching (#38762)Claude Code
  • fd822b07fix(text-splitters): restore lazy imports for heavy optional dependencies Claude Code
  • 67fa96ffdocs(groq): remove duplicate `method` block from `with_structured_output` GitHub Copilot
  • 5650448afeat(core): incorporate gateway metadata to traces (#39703)GitHub Copilot
  • e939c967fix: compaction typo (#35467)GitHub Copilot

What was excluded

Commits in window1,520
Merge commits removed0
CI / dependency bots removed624
Considered896

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli langchain-ai/langchain

Scan another repository