Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
Assisted or autonomous
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
Peak month: 22.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 139 | 11% |
| GitHub Copilot | GitHub | 30 | 2.4% |
| Cursor Agent | Anysphere | 14 | 1.1% |
| Gemini CLI | 2 | 0.2% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
7843291cfix(benchmarks): explicit utf-8 encoding + ASCII-safe print chrome on WindClaude Code698a1c6dfix(embedding): never let CoreML return NaN vectors for embeddinggemmaClaude Code18cf07fcfix(repair): check the FTS5 content table before rebuilding from it (#2278Claude Code656e0a4dtest(backends): cover the _embed_texts fallback and empty-batch guardGitHub Copilot73772cb7Potential fix for pull request findingGitHub Copilot5f0a2140style: format hook testsGitHub Copilot352eb67atest: update Cursor followup assertion for checkpoint toolCursor Agentf3ed6f79fix: harden tool_checkpoint input validationCursor Agent4291fecffeat: add mempalace_checkpoint batch save toolCursor Agent178105cbfeat: optimize metadata counting using Qdrant server-side facets (#1868)Gemini CLI526d58aeUpdate tests/test_hallways_pagination.pyGemini CLI
What was excluded
| Commits in window | 1,947 |
| Merge commits removed | −638 |
| CI / dependency bots removed | −41 |
| Considered | 1,268 |
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 MemPalace/mempalace