- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Build voice agents with open-source models
01Result
huggingface/speech-to-speech ↗huggingface/speech-to-speech AI coding statistics: 1.2%
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 | 12.2% | 49 |
| 2026-03 | 0% | 78 |
| 2026-04 | 0% | 48 |
| 2026-05 | 0% | 76 |
| 2026-06 | 3.4% | 29 |
| 2026-07 | 1.5% | 65 |
| 2026-08 | 0% | 247 |
| 2026-09 | 0% | 59 |
Peak month: 12.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 6 | 0.9% |
| Cursor Agent | Anysphere | 1 | 0.2% |
| GitHub Copilot | GitHub | 1 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
5700e88eon GitHubAdd chat-completions LLM backend (OpenAI /v1/chat/completions) (#322)Claude Code00cf7ee6on GitHubAdd WebSocket connection mode for bidirectional audio streamingClaude Code9f1ffa76on GitHubAdd Pocket TTS supportClaude Code3935afc5on GitHubAdd mic/speaker device selectors to the demo Settings UI.Cursor Agent79c76d40on GitHubUpdate README.mdGitHub 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 | 876 |
| Merge commits removed | −213 |
| CI / dependency bots removed | −12 |
| Considered | 651 |
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 huggingface/speech-to-speech