- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
The Open Source Trading Ecosystem for Everyone.
01Result
marketcalls/openalgo ↗marketcalls/openalgo AI coding statistics: 77.9%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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 | 66.2% | 231 |
| 2026-03 | 79% | 138 |
| 2026-04 | 87.5% | 184 |
| 2026-05 | 98.4% | 127 |
| 2026-06 | 91% | 155 |
| 2026-07 | 91% | 245 |
| 2026-08 | 57.7% | 376 |
| 2026-09 | 81.4% | 145 |
Peak month: 98.4%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 1247 | 77.9% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
8986ba53on GitHubfix(agent): one brand mark on a chat chart, and the combination aloneClaude Code4dfe2568on GitHubfeat(agent): draw the combined premium with the platform chart, and study Claude Code9f4767d0on GitHubfeat(strategybuilder): draw both chart tabs with the OpenAlgo engineClaude 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 | 2,172 |
| Merge commits removed | −254 |
| CI / dependency bots removed | −317 |
| Considered | 1,601 |
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 marketcalls/openalgo