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.

A clean, modular SDK for building AI agents with OpenHands V1.

01Result

OpenHands/software-agent-sdk ↗

OpenHands/software-agent-sdk AI coding statistics: 74.3%

of 1,300 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
74.3% agent · top contributor 15.8%72 contributors
org-wide

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

966
agent commits
334
other considered commits
72
agent contributors
15.8%
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

956assisted
10autonomous

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
2026-0289.3%177
2026-0377.8%185
2026-0475.5%163
2026-0576.1%213
2026-0669.5%233
2026-0760.4%139
2026-0867%115
2026-0974.7%75

Peak month: 89.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Other / generic agentVarious84765.2%
Claude CodeAnthropic14511.2%
GitHub CopilotGitHub30.2%
OpenAI CodexOpenAI10.1%
DevinCognition10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8224a0ab on GitHubfeat(agent-server): publish python-minimal image (#5088)Other / generic agent
  • 481dfb3d on GitHubRelease v1.48.0 (#5079)Other / generic agent
  • 4c89b689 on GitHubfix(agent-server): use a minimal Debian Python/Node runtime (#5077)Other / generic agent
  • b054a2fe on GitHubfix(agent-server): enforce the paginated search limit (#4991)Claude Code
  • 15a9b860 on GitHubfeat(profiles): scope which secrets an agent profile receives (#4931)Claude Code
  • 57f5cc9f on GitHubfix(acp): materialise only the running provider's file secrets (#4927)Claude Code
  • be6cd3b8 on GitHubfix(settings): inherit condenser max_tokens from LLM effective_max_input_tGitHub Copilot
  • 772fb8d2 on GitHubRefine temperature/top_p handling for reasoning models (#2277)GitHub Copilot
  • aa3e50dc on GitHubFeat: session recording agent's browser sessions (#1731)GitHub Copilot
  • 704cbe60 on GitHubfeat: move TypeScript client into monorepo (#4702)OpenAI Codex
  • b015eb17 on GitHubfix(sdk): URL-encode session_api_key in WebSocket query parameter (#3558)Devin

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 window1,394
Merge commits removed−0
CI / dependency bots removed−94
Considered1,300

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 →Devin commitsBrowse repositories with detected Devin 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 OpenHands/software-agent-sdk

Scan another repository

Try