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.

Exploit Development and Reverse Engineering with GDB & LLDB Made Easy

01Result

pwndbg/pwndbg ↗

pwndbg/pwndbg AI coding statistics: 5.7%

of 315 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.7% agent · top contributor 50%7 contributors

team

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

agent commits

297

other considered commits

agent contributors

50%

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

18assisted

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: 13.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	15	4.8%
GitHub Copilot	GitHub	3	1%

03Evidence

Inspect the matches

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

Matched commit samples

55596aa6 on GitHubbump pwndbg 2026.09.15Claude Code
aacb899a on GitHublldb: Don't crash the REPL on a malformed command lineClaude Code
5de5e9c4 on GitHubAnnotate run_gdb_with_script and the remote pipe test for mypy --strictClaude Code
03329acd on GitHubChange MAX_SIZE to SIZE_MAX in realloc testGitHub Copilot
6f63c903 on GitHubSpeed up kernel image downloads by parallelizing wget calls (#3972)GitHub Copilot
f821bbcf on GitHubPrint nested field offsets recursively in dt (#3862)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 window	347
Merge commits removed	−0
CI / dependency bots removed	−32
Considered	315

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 pwndbg/pwndbg

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	1.5%	66
2026-03	8.3%	24
2026-04	6.7%	15
2026-05	13.3%	30
2026-06	5.4%	37
2026-07	7.3%	41
2026-08	4.3%	47
2026-09	5.5%	55