← the index
stanfordnlp/dspy
13.2%
of 273 commits were committed by an AI agent — a floor, not an estimate
13.2% agent · top contributor 19.4%20 contributors
org-wide

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

36
agent commits
237
human commits
20
agent contributors
19.4%
largest contributor

Assisted or autonomous

36assisted
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: 34.2%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic3211.7%
GitHub CopilotGitHub31.1%
DevinCognition10.4%

Verify it yourself

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

  • 6fb74fcffeat(dspy): dspy.settings.interpreter_factory overrides default PythonInteClaude Code
  • b04a0733perf(dspy): defer anyio, openai and jiter to their use sites (#10381)Claude Code
  • 515aa8eefeat(clients): allow disable caching to support runtimes without a file syClaude Code
  • 9e8a323dUpdate DspyGEPAResult and documentation for gepa 0.1.1 changes (#9673)GitHub Copilot
  • 3dde431bfix(dspy): SemanticF1 and CompleteAndGrounded now return dspy.Prediction (GitHub Copilot
  • 098091fcfix(interpreter): Fix enable_read_paths with multiple files (#9256)GitHub Copilot
  • 027d9f45ci: pin ollama image to 0.31.2 and add warm-up health check (#10041)Devin

What was excluded

Commits in window345
Merge commits removed2
CI / dependency bots removed70
Considered273

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 stanfordnlp/dspy

Scan another repository