Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

01Result

sierra-research/tau2-bench ↗

sierra-research/tau2-bench AI coding statistics: 26.4%

of 163 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.4% agent · top contributor 46.5%9 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

43
agent commits
120
other considered commits
9
agent contributors
46.5%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

43assisted
0autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0233.3%3
2026-035%20
2026-040%62
2026-0531.6%19
2026-0633.3%6
2026-0789.7%29
2026-0850%14
2026-090%10

Peak month: 89.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic2817.2%
Cursor AgentAnysphere159.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 1eceb045 on GitHubfeat: generic parallel runner — controller + worker processes (tau2 run --Claude Code
  • 35b60b48 on GitHubfeat: track usage and cost for audio-native voice agents (#454)Claude Code
  • e6609f3d on GitHubchore: add .worktreeinclude so Claude Code worktrees get .env (#453)Claude Code
  • 668d3bcd on GitHubAdd grok-voice-think-fast-2.0 voice leaderboard submission (#460)Cursor Agent
  • e5e51b3d on GitHubAdd qwen3.5-omni-plus-realtime voice leaderboard submission (#458)Cursor Agent
  • 62ba4058 on GitHubfeat: expose qwen as --audio-native-provider CLI choice (#450)Cursor Agent

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 window172
Merge commits removed−9
CI / dependency bots removed−0
Considered163

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

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 sierra-research/tau2-bench

Scan another repository

Try