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.

Stateful agents that are like people, with memory, identity, and the ability to learn and adapt

01Result

letta-ai/letta-code ↗

letta-ai/letta-code AI coding statistics: 1.5%

of 2,171 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.5% agent · top contributor 45.5%9 contributors
org-wide

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

33
agent commits
2,138
other considered commits
9
agent contributors
45.5%
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

29assisted
4autonomous

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
2026-010%13
2026-021%389
2026-030.3%308
2026-040%283
2026-050.2%426
2026-060.7%302
2026-072.3%216
2026-0811.9%151
2026-092.4%83

Peak month: 11.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic241.1%
DevinCognition40.2%
Cursor AgentAnysphere30.1%
GitHub CopilotGitHub20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7a74f3b9 on GitHubfix(cli): settle Esc interrupts from the turn owner so queued notificationClaude Code
  • bb329261 on GitHubfix(subagents): drop stale Claude-Code-derived tools (LS/MultiEdit/TodoWriClaude Code
  • 0c608d4f on GitHubdocs(tools): route agents to Monitor from Bash and BashOutput descriptionsClaude Code
  • 9bc6ccf8 on GitHubfeat(whatsapp): add messaging controls and lifecycle hardening (#3650)Devin
  • 7ddc3062 on GitHubfeat(whatsapp): canonicalize LID identities (#3599)Devin
  • f77abc8e on GitHubfeat: add GLM 5.2 to model registry (#2940)Devin
  • 5914b085 on GitHubfix: label xhigh Extra High when catalog has a max tier [LET-11121] (#3896Cursor Agent
  • cfa0b221 on GitHubfix: remap unsupported minimal reasoning for GPT-5.6 [LET-11064] (#3877)Cursor Agent
  • c5970804 on GitHubfix(channels): keep typing active across queued turns (#3786)Cursor Agent
  • b100c2d1 on GitHubfix(tui): prevent malformed questions from crashing approval UI (#4422)GitHub Copilot
  • 0fb8bfd2 on GitHubfeat(protocol): expose conversation cwd map (#2433)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 window2,631
Merge commits removed−2
CI / dependency bots removed−458
Considered2,171

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 letta-ai/letta-code

Scan another repository

Try