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.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

01Result

MervinPraison/PraisonAI ↗

MervinPraison/PraisonAI AI coding statistics: 27.7%

of 2,396 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.7% agent · top contributor 45.7%18 contributors
org-wide

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

663
agent commits
1,733
other considered commits
18
agent contributors
45.7%
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

490assisted
173autonomous

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
2026-020%46
2026-033.4%238
2026-0423.3%378
2026-0549.2%124
2026-0631.7%344
2026-0711.9%514
2026-0835.4%478
2026-0960.9%274

Peak month: 60.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic39316.4%
Cursor AgentAnysphere1516.3%
GitHub CopilotGitHub1365.7%
Gemini CLIGoogle10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 72ee27a4 on GitHubtest(bus): the EventBus suite asserted a contract and its oppositeClaude Code
  • 268fd8d7 on GitHubtest(code): ten tests were reading the developer's machine, not the codeClaude Code
  • 225dae3d on GitHubfix: circuit breaker counted every outcome twice; trust lookup failed openClaude Code
  • 79343b01 on GitHubfeat(ci): dual OAuth pre-flight probe and failover (v1.1.8)Cursor Agent
  • 6a485506 on GitHubfix(ci): merge-only waits for Opus verdict on busy PRsCursor Agent
  • f625d4b3 on GitHubfix(ci): use GitHub MCP get_* tool names in merge gate assess (#4926)Cursor Agent
  • bc73dd1d on GitHubIssue #1540: Changes from Claude (#1792)GitHub Copilot
  • 52162749 on GitHubfix: Gateway Telegram polling path bypasses security controls (fixes #1747GitHub Copilot
  • 2e5eca1d on GitHubfix: disable streaming by default in sync chat methods (fixes #1733) (#173GitHub Copilot
  • 4e6c6af7 on GitHubfeat: blueprint catalogue and consent-first suggestion mechanism (#2169)Gemini CLI

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 window6,562
Merge commits removed−1,491
CI / dependency bots removed−2,675
Considered2,396

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 MervinPraison/PraisonAI

Scan another repository

Try