- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Zero-cloud AI memory that works everywhere. SQLite-backed. One pure-Python dependency.
01Result
mnemosyne-oss/mnemosyne ↗mnemosyne-oss/mnemosyne AI coding statistics: 10.7%
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 |
|---|---|---|
| 2026-04 | 0% | 111 |
| 2026-05 | 20.5% | 376 |
| 2026-06 | 4.4% | 180 |
| 2026-07 | 7.9% | 140 |
| 2026-08 | 9.7% | 237 |
| 2026-09 | 2.4% | 84 |
Peak month: 20.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 120 | 10.6% |
| GitHub Copilot | GitHub | 1 | 0.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
904cd6d3on GitHubfeat(mcp): declare the per-call bank parameter every tool already honours Claude Code552cb9c1on GitHubdocs: remove the Hermes Tweet compatibility entry (#916)Claude Code98fc3b64on GitHubdocs: point ProductHunt badge at the current product pageClaude Codefd05d85eon GitHubfeat(mcp): auto-load .env configuration and add --env-file option (#516)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 | 1,300 |
| Merge commits removed | −172 |
| CI / dependency bots removed | −0 |
| Considered | 1,128 |
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 mnemosyne-oss/mnemosyne