- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints
01Result
Soju06/codex-lb ↗Soju06/codex-lb AI coding statistics: 26.5%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 0% | 48 |
| 2026-03 | 0% | 99 |
| 2026-04 | 2% | 99 |
| 2026-05 | 0.6% | 161 |
| 2026-06 | 0.9% | 111 |
| 2026-07 | 41.5% | 224 |
| 2026-08 | 35% | 240 |
| 2026-09 | 59.7% | 238 |
Peak month: 59.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 312 | 25.6% |
| Cursor Agent | Anysphere | 6 | 0.5% |
| GitHub Copilot | GitHub | 3 | 0.2% |
| OpenAI Codex | OpenAI | 2 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
f94dd509on GitHubfix(utils): consume a shared future's exception when no waiter is left (#2Claude Code982125a3on GitHubrevert(overflow): remove the subscription-exhaustion model-source fallbackClaude Code837964b9on GitHubfeat(auth): add an OIDC identity provider with UI-configured, encrypted coClaude Code6d788664on GitHubfix(proxy): keep source Responses SSE alive and normalized (#1854)Cursor Agent09dd9348on GitHubfix(proxy): exclude previous_response_id from model-source routing (#1859)Cursor Agent254839f5on GitHubfix(proxy): preserve explicit null embedding fields (#1836)Cursor Agentc8fcc65aon GitHubfeat(proxy): add SOCKS4/SOCKS5 outbound proxy support via env vars (#1008)GitHub Copilota8cbefa8on GitHubrefactor: upgrade error handling and replace print with standard logging iGitHub Copilot36a4e7cbon GitHubdocs: add comprehensive docstrings to select_account in logic.py (#350)GitHub Copilot7a0b6719on GitHubfix(proxy): durably recover hard HTTP bridge operations (#1657)OpenAI Codex6b1cb47eon GitHubfix(chat): resolve parallel tool_call argument duplication via output_indeOpenAI 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 window | 1,404 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −183 |
| Considered | 1,220 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 Soju06/codex-lb