← the index
getzep/graphiti
52.9%
of 153 commits were committed by an AI agent — a floor, not an estimate
52.9% agent · top contributor 39.5%12 contributors
org-wide

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

81
agent commits
72
human commits
12
agent contributors
39.5%
largest contributor

Assisted or autonomous

81assisted
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
Sep26

Peak month: 83.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic6643.1%
Cursor AgentAnysphere149.2%
GitHub CopilotGitHub10.7%

Verify it yourself

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

  • 2d96f271fix(falkordb): avoid a full :Entity scan per hit in edge_fulltext_search (Claude Code
  • 23330cbcHonor NEO4J_DATABASE in MCP serverClaude Code
  • 993e081afix(attributes): preserve prior node attributes when no entity type applieClaude Code
  • eaa41286Bump graphiti-core to 0.30.2 (#1858)Cursor Agent
  • 3ff5c160Land contributor fixes from #1686 #1689 #1720 #1761 (#1856)Cursor Agent
  • 11538f6dbump mcp server to 1.1.0 with graphiti-core 0.30.1Cursor Agent
  • 0290e4dePotential fix for code scanning alert no. 26: Workflow does not contain peGitHub Copilot

What was excluded

Commits in window241
Merge commits removed0
CI / dependency bots removed88
Considered153

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 getzep/graphiti

Scan another repository