sierra-research/tau2-bench
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
2.2k stars · 579 forks · Python
Healthy
Healthy: actively maintained by 10 people, no known risks.
Why
No rule fired.
What would change this
- A dormant maintenance status, a deprecated or archived package, a successor link, or a critical advisory would change this.
Maintenance
CompleteActive
- Human commits, 30 days
- 10
- Human commits, 90 days
- 47
- Human commits, 365 days
- 200
- Bot share of commits, 365 days
- 0%
- Last commit
- Oct 14, 2026 (10 hours ago)
- Last human commit
- Oct 14, 2026 (10 hours ago)
- Authors, 90 days
- 10
- Last release
- Jul 22, 2026 (2 months ago)
- Median PR merge time
- 2 hours
Responsiveness: of 30 recent issues, 3% got a maintainer reply. Median first response: 9 days.
Sources: Commits, Releases, Merged pull requests, Issues
People
Complete- Owner
- Organization
- Commits sampled
- 200 since Oct 15, 2025
- Authors for half of commits
- 2
- Authors for 80% of commits
- 4
- Contributors
- 18
Top committers
- keshav-sierra: 32% of commits
- victorbarres: 28% of commits
- benshi34: 16% of commits
- soham-sierra: 12% of commits
- zyteka: 6% of commits
Sources: Commits, Contributors
Stars
CompleteOrganic, confidence medium
Bursts
- Nov 24, 2025 to Nov 25, 2025: about 33 more stars than usual, peak 22 in one day, a spike that tapers off. Outside explanation: a jump in forks, a jump in issues and pull requests.
Anyone can buy stars for any repo; bursts alone don't prove the owner did.
- The star history looks organic.
Sources: How star history is analyzed
Risk
CompleteFlags
No risk flags.
License
- Now
- MIT (OSI-approved)
- A year ago
- MIT (OSI-approved)
Packages
No published packages found.
Sources: GitHub: sierra-research/tau2-bench
Badge
Add this to a README to show the current verdict:
[](https://reporadar.ai/sierra-research/tau2-bench)Earlier verdicts
- Oct 15, 2026: Healthy
- Oct 14, 2026: Healthy
Computed 3 hours ago · method 2026.10.2