← the index
assafelovic/gpt-researcher ↗
25.9%
of 170 commits were committed by an AI agent — a floor, not an estimate
25.9% agent · top contributor 63.6%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

44
agent commits
126
human commits
8
agent contributors
63.6%
largest contributor

Assisted or autonomous

44assisted
0autonomous

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

Peak month: 90%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic2917.1%
GitHub CopilotGitHub84.7%
Cursor AgentAnysphere74.1%

Verify it yourself

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

  • a1675268feat(retrievers): declare whether results need scrapingClaude Code
  • ff79a891fix: make the empty-source-urls notification reachableClaude Code
  • d95af0ecchore: remove the dead poetry dependency block, test the declared floorClaude Code
  • 26de2275docs(pr): add Brave snippet PR descriptionGitHub Copilot
  • 9901f94bdocs(pr): add Anthropics cost tracking PR descriptionGitHub Copilot
  • 563cae68feat(cost): track Anthropic usage metadataGitHub Copilot
  • 6d0cf55aTrack benchmark run artifacts and swap FRAMES for the report head-to-headCursor Agent
  • 20bd9569Headline the hybrid benchmark's 94% peak coverage instead of the rangeCursor Agent
  • 45676464Harden hybrid benchmark: realistic corpus and a DIY file-tools baseline arCursor Agent

What was excluded

Commits in window267
Merge commits removed−96
CI / dependency bots removed−1
Considered170

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 assafelovic/gpt-researcher

Scan another repository

Try