- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
01Result
xbtlin/ai-berkshire ↗xbtlin/ai-berkshire AI coding statistics: 52.6%
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 | 77.4% | 164 |
| 2026-05 | 42% | 312 |
| 2026-06 | 75.8% | 693 |
| 2026-07 | 1.2% | 162 |
| 2026-08 | 0.8% | 121 |
| 2026-09 | 0% | 41 |
Peak month: 77.4%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 785 | 52.6% |
| 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
f45bb8c0on GitHubfix(tools): 修复 report_audit 数字提取丢负号与两个工具的 Windows GBK 崩溃 (#84)Claude Code726d35d1on GitHubClaude/finmind taiwan stock integration nho04m (#72)Claude Code9ae86315on GitHub瓶颈猎手扫描 2026-06-26 第305轮:无新信号Claude Codec149b49bon GitHub同步 codex-prompts:修复 deep-company-series 标题漂移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 | 1,500 |
| Merge commits removed | −7 |
| CI / dependency bots removed | −0 |
| Considered | 1,493 |
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 xbtlin/ai-berkshire