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

run-llama/llama_index ↗

run-llama/llama_index AI coding statistics: 3%

of 400 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3% agent · top contributor 25%10 contributors
org-wide

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

12
agent commits
388
other considered commits
10
agent contributors
25%
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

12assisted
0autonomous

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
2026-022.8%108
2026-033.5%115
2026-045.7%35
2026-052.4%42
2026-067.7%13
2026-072.8%36
2026-080%40
2026-090%11

Peak month: 7.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic102.5%
Cursor AgentAnysphere20.5%
GitHub CopilotGitHub20.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 791f6251 on GitHubfeat(vector-stores/vertexai): Expand support of V2 API for `VertexAIVectorClaude Code
  • 623a7c9e on GitHubRemove outdated llama-index-tools-scrapegraph integration (#21415)Claude Code
  • 5ef6504c on GitHubfix(google-genai): pass DocumentBlock.title as display_name to File API (#Claude Code
  • 791f6251 on GitHubfeat(vector-stores/vertexai): Expand support of V2 API for `VertexAIVectorCursor Agent
  • 31e88711 on GitHubfeat(rate_limiter): add SlidingWindowRateLimiter for strict per-minute capCursor Agent
  • 791f6251 on GitHubfeat(vector-stores/vertexai): Expand support of V2 API for `VertexAIVectorGitHub Copilot
  • f8eff608 on GitHubfix: pass `delete_from_docstore` parameter in `BaseIndex.delete_ref_doc` (GitHub Copilot

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 window489
Merge commits removed−0
CI / dependency bots removed−89
Considered400

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
run-llama/llama_index
Default branch
main
Resolved HEAD
fd4a517ad6490f0c8464a13fdf133760b696434a ↗
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 position35th percentile

Midrank percentile; equal shares split the tied positions.

Repository
3%
Cohort median
6.3%
Share rank
161 / 247
0th50th100th

Percentile = (repositories below + half of 3 tied repositories) ÷ 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 →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 run-llama/llama_index

Scan another repository

Try