Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

bytedance/deer-flow ↗

bytedance/deer-flow AI coding statistics: 21%

of 2,054 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
21% agent · top contributor 6.9%124 contributors
org-wide

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

432
agent commits
1,622
other considered commits
124
agent contributors
6.9%
largest contributor

02Drivers

What shapes this result

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

Assisted or autonomous

429assisted
3autonomous

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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0232.6%362
2026-0332.9%216
2026-0427.1%251
2026-0525.5%157
2026-0621.3%211
2026-0712.1%464
2026-088.4%191
2026-098.9%202

Peak month: 32.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic23911.6%
GitHub CopilotGitHub1487.2%
Cursor AgentAnysphere683.3%
OpenAI CodexOpenAI20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 740dbc4b on GitHubfix(subagents): keep the subagent system prompt through context compactionClaude Code
  • 99902b77 on GitHubfix(agents): keep token budget signals for runs without a run_id (#5436)Claude Code
  • 0a0d7681 on GitHubfix(goal): stand the goal down once the run has hit its token budget (#542Claude Code
  • dfaeef37 on GitHubfix(frontend): support standalone demo APIs and runtime GitHub stars (#530GitHub Copilot
  • 23d8e4b3 on GitHubfeat(scripts): support skipping frontend build on make start (#5053)GitHub Copilot
  • 062ba9dd on GitHubfeat: integrate MiniMax Code as a native ACP agent (#4846)GitHub Copilot
  • 851e7666 on GitHubfix(docker): don't abort Docker startup when .env is missing (#4956)Cursor Agent
  • ea9b7014 on GitHubfix(clarification): drop sibling tool calls before interrupt (#4908)Cursor Agent
  • fd41fdb0 on GitHubfeat(middleware): add structured tool result meta and tool-progress state Cursor Agent
  • c542185a on GitHubfeat(extensions): add gateway contribution points and packaged extension mOpenAI Codex
  • e119dc74 on GitHubfeat(codex): support explicit OpenAI Responses API config (#1235)OpenAI Codex

04Method

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 window2,162
Merge commits removed−37
CI / dependency bots removed−71
Considered2,054

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
bytedance/deer-flow
Default branch
main
Resolved HEAD
b0cb3a3a8cc15b2723581c11855b06560da17dda ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position78th percentile

Midrank percentile; equal shares split the tied positions.

Repository
21%
Cohort median
6.3%
Share rank
56 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
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 bytedance/deer-flow

Scan another repository

Try