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.

Exa MCP for web search and web crawling!

01Result

exa-labs/exa-mcp-server ↗

exa-labs/exa-mcp-server AI coding statistics: 49.4%

of 176 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

49.4% agent · top contributor 41.4%9 contributors

org-wide

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

agent commits

other considered commits

agent contributors

41.4%

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

34assisted

53autonomous

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: 81.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Devin	Cognition	63	35.8%
Claude Code	Anthropic	24	13.6%

03Evidence

Inspect the matches

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

Matched commit samples

40d9990f on GitHubdocs: add Replit setup instructions and install badge (#268)Devin
ad888a18 on GitHubfeat: set server name to 'Exa' and add icon per MCP spec (#341)Devin
5ce6c53b on GitHubfix(mcp): align OAuth protected resource metadata (#340)Devin
25332213 on GitHubfix(web_fetch_exa): honor maxCharacters by sending correct /contents payloClaude Code
1ef463ba on GitHubfix(mcp): signal error=invalid_token in WWW-Authenticate on JWT failure (#Claude Code
96c78537 on GitHubfix(mcp): return 401 when Bearer JWT fails OAuth verification (#336)Claude 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 window	206
Merge commits removed	−30
CI / dependency bots removed	−0
Considered	176

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 →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 exa-labs/exa-mcp-server

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	81.8%	22
2026-03	76.9%	39
2026-04	41.2%	68
2026-05	75%	12
2026-06	20%	10
2026-07	0%	12
2026-08	0%	13