- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Rust implementation of the Ethereum Virtual Machine.
01Result
bluealloy/revm ↗bluealloy/revm AI coding statistics: 2.2%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 | 9.4% | 32 |
| 2026-03 | 0% | 43 |
| 2026-04 | 0% | 49 |
| 2026-05 | 0% | 36 |
| 2026-06 | 4.8% | 21 |
| 2026-07 | 4.2% | 24 |
| 2026-08 | 0% | 20 |
| 2026-09 | 0% | 7 |
Peak month: 9.4%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 3 | 1.3% |
| GitHub Copilot | GitHub | 2 | 0.9% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
4a646d2con GitHubfeat(examples): flush out custom frame usage in my_evm example (#3825)Claude Code939b879aon GitHubfix(interpreter): use IntoAddress in pop_address to avoid const-eval panicClaude Codecab55fdaon GitHubfix(database): allow EIP161 state clear for empty Loaded and Changed accouClaude Codefea169f2on GitHubfeat(revme): validate block gas used in blockchain tests (#3416)GitHub Copilot0ee852ceon GitHubrefactor!: add ResultGas struct to ExecutionResult (#3413)GitHub Copilot
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 | 284 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −52 |
| Considered | 232 |
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 bluealloy/revm