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.

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

01Result

maximhq/bifrost ↗

maximhq/bifrost AI coding statistics: 1.6%

of 3,238 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
1.6% agent · top contributor 7.5%38 contributors
org-wide

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

53
agent commits
3,185
other considered commits
38
agent contributors
7.5%
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

53assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-022%200
2026-031.5%331
2026-041.6%322
2026-050.2%462
2026-062.3%487
2026-073.5%545
2026-081.2%516
2026-090.5%375

Peak month: 3.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic411.3%
Cursor AgentAnysphere110.3%
GitHub CopilotGitHub10%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 872cd703 on GitHubfix(gemini): keep generationConfig ExtraParams intact across retries (#713Claude Code
  • 2f4b586d on GitHub[fix]: ui - declare VKCreationPolicyResponse in the OSS access-profile falClaude Code
  • 73b0ceef on GitHub[fix]: framework/tracing - emit BilledUsage token and cost attributes on fClaude Code
  • d9339e68 on GitHubperf(anthropic): avoid copying known request fields (#5809)Cursor Agent
  • f7d30c36 on GitHub[fix]: clear stuck entity-assignment validation on virtual key sheet (#580Cursor Agent
  • c6f0dcd0 on GitHubfeat(vertex): allow Flex PayGo for gemini-3.5-flash-lite (#5598)Cursor Agent
  • 93cca7c7 on GitHubfix: set octet-stream Content-Type on pprof endpoints for scraper compatibGitHub Copilot
  • 05e688e9 on GitHubadd model catalog pricing (#5033)OpenAI Codex

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 window4,278
Merge commits removed−227
CI / dependency bots removed−813
Considered3,238

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Go AI coding statisticsCompare evidence across Go 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 maximhq/bifrost

Scan another repository

Try