Skip to content

(=^•^ωᴗ•^^=)holt home

Check a repo How it works Pricing

try an example sign in

Check a repo How it works Pricing try an example

Loading…

Holt

Reads a project's public pull request history on GitHub. It never posts, comments or contacts anyone.

Open source, Apache-2.0

Find a project
Browse projects
How it works

Badge for maintainers
Pricing
Source on GitHub

Terms
Privacy
Refunds
Contact
Team

Loading the report…

Loading starter issues…

sierra-research/tau2-bench: Worth your time? · Holt

sierra-research/tau2-bench

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

2.2k stars558forks114issuespushed 8 days ago

taubench.com ↗github.com/sierra-research/tau2-bench ↗

Merge plancoming soon

Share on WhatsApp (opens in a new tab)Share on X (opens in a new tab)Share on LinkedIn (opens in a new tab)

Long shot

rules report

(=^･_･^=)

Only 6 of the 37 people who sent their first pull request here got it merged.

9 of 86outside PRs merged (10%)

checked 3 hours ago

Starter issues

README

Where newcomer work lands

The evidence

sign in to see the full report →