{"slug":"terminal-bench","name":"Terminal-Bench","kind":"tool","deliveryMethods":["tool"],"kindLabel":"Tool","grade":"B","score":73,"tagline":"Benchmark and harness for evaluating AI agents on end-to-end tasks in real terminal environments.","description":"Terminal-Bench is the benchmark for testing AI agents in real terminal environments. From compiling code to training models and setting up servers, Terminal-Bench evaluates how well agents can handle real-world, end-to-end tasks - autonomously.","tags":["evaluation","cli","terminal-tasks"],"url":"https://way.space/tool/terminal-bench","stars":"—","category":"qa","categories":["qa","coding"],"repo":"https://github.com/harbor-framework/terminal-bench-1","website":"https://www.tbench.ai/","license":"Apache-2.0","maintainers":[{"login":"harbor-framework","url":"https://github.com/harbor-framework","isMember":false,"verified":false},{"login":"li-boxuan","url":"https://github.com/li-boxuan","isMember":false,"verified":false},{"login":"ibercovich","url":"https://github.com/ibercovich","isMember":false,"verified":false}],"scoreWhy":[{"label":"Contributors & bus-factor","detail":"36 recent contributors","direction":"positive"},{"label":"Commit recency","detail":"last commit 62d ago","direction":"positive"},{"label":"Commit cadence","detail":"1 commits in 90 days","direction":"positive"},{"label":"Issue close ratio","detail":"53% of issues closed","direction":"positive"},{"label":"Release cadence","detail":"0 releases in 12 months","direction":"negative"},{"label":"Stars (log-damped)","detail":"2,575 stars (log-damped)","direction":"positive"},{"label":"Star authenticity","detail":"star-velocity check unavailable — GitHub no longer publishes stargazer timestamps for this repo","direction":"neutral"},{"label":"Engagement-to-star ratio","detail":"healthy engagement (0.80 per star)","direction":"positive"}]}