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.

Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step.

01Result

julep-ai/julep ↗

julep-ai/julep AI coding statistics: 75.6%

of 422 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

75.6% agent · top contributor 91.2%2 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

319

agent commits

103

other considered commits

agent contributors

91.2%

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

319assisted

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.

Agent share by month

Peak month: 90.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	316	74.9%
OpenAI Codex	OpenAI	3	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

cbe02775 on GitHubchore(release): bump version to 3.0.0rc6Claude Code
420a0b5d on GitHubfix(deploy): report smoke-test Job logs when helm test failsClaude Code
9247c59e on GitHubfix(worker)!: default Temporal payload encryption to requiredClaude Code
bb94f50c on GitHubTF-7: per-component split via .as_sub (own deployment unit; attenuated; TeOpenAI Codex
830c06c3 on GitHubTF-6 fix: reject plain-Flow capability that calls ungranted tools (CAP_APPOpenAI Codex
1709eae1 on GitHubTF-5 fix: registry idempotency compares normalized IR (ignore provisional 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 window	464
Merge commits removed	−39
CI / dependency bots removed	−3
Considered	422

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

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python repositories →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 julep-ai/julep

Scan another repository

Try

Month	Agent share	Considered commits
2026-06	90.7%	281
2026-07	45.4%	141