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.

High-performance AI coding agent CLI written in Rust with zero unsafe code

01Result

Dicklesworthstone/pi_agent_rust ↗

Dicklesworthstone/pi_agent_rust AI coding statistics: 52.1%

of 5,236 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
52.1% agent · top contributor 80.4%6 contributors
individual

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

2,726
agent commits
2,510
other considered commits
6
agent contributors
80.4%
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

2726assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0279.4%2052
2026-0367.2%503
2026-0464.8%264
2026-0516.4%701
2026-0694.4%36
2026-0793.9%33
2026-0815.2%1378
2026-0974%269

Peak month: 94.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic272652.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 15807802 on GitHubchore(perf): rebind budget reports after the failover extraction workClaude Code
  • cf0faca7 on GitHubrefactor(agent): one failover transition for print mode and RPCClaude Code
  • 29158986 on GitHubfeat(ftui): the default interactive stack now retries transient failuresClaude Code

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 window5,279
Merge commits removed−37
CI / dependency bots removed−6
Considered5,236

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 →Rust AI coding statisticsCompare evidence across Rust 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 Dicklesworthstone/pi_agent_rust

Scan another repository

Try