Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Open-source, secure environment with real-world tools for enterprise-grade agents.

e2b-dev/E2B ↗

e2b-dev/E2B AI coding statistics: 67.7%

of 362 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
67.7% agent · top contributor 63.7%18 contributors
team

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

245
agent commits
117
other considered commits
18
agent contributors
63.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

174assisted
71autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0214.3%35
2026-0333.3%24
2026-0476.5%17
2026-0533.3%27
2026-0672.2%90
2026-0785.5%62
2026-0897.1%69
2026-0965.8%38

Peak month: 97.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic17548.3%
DevinCognition6116.9%
Cursor AgentAnysphere123.3%
GitHub CopilotGitHub41.1%

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 956e3ab8 on GitHubfix(sdk): apply the upload headers the API returns with a file upload linkClaude Code
  • 80496c0f on GitHubtest(js-sdk): run the full unit test suite in a browser (#1609)Claude Code
  • 08efa361 on GitHubfeat(sdk): add httpsPorts network config for HTTPS sandbox backends (#1546Claude Code
  • e1fbe86b on GitHubchore(deps): scheduled dependency updates for js-sdk / cli / python-sdk (#Devin
  • 804021ee on GitHubtest: skip the deprecated git suites unless ENABLE_GIT_TESTS is set (#1863Devin
  • 12e314d6 on GitHubchore: bump smol-toml override to ^1.7.1 for security advisory (#1867)Devin
  • d55ddb8b on GitHubtest(python-sdk): drop build API path encoding integration tests (#1713)Cursor Agent
  • 43c28b15 on GitHubci(js-sdk): install Playwright Chromium without `--with-deps` (#1699)Cursor Agent
  • 53676931 on GitHubfix(sdk): omit autoResume from the create request when unset (#1694)Cursor Agent
  • 8b8a224f on GitHubfeat(python-sdk): add logger option for request/debug logging (#1409)GitHub Copilot
  • 59057f5a on GitHubPotential fix for code scanning alert no. 3: Workflow does not contain perGitHub Copilot
  • 17130809 on GitHubPotential fix for code scanning alert no. 4: Workflow does not contain perGitHub Copilot

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window459
Merge commits removed−3
CI / dependency bots removed−94
Considered362

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli e2b-dev/E2B

Scan another repository