CASE 01AutomationBench / Marketing
Get your work doneat top GEAR.
Don’t let your work wait. GEAR brings recursive self-improvement (RSI) to your agent’s harness — using task feedback to continually refine skills, tools, and workflows for the work that matters.
Bring the agent you already use.
CodexClaude CodeDSHPi+
GEAR-tuned harness.
Beyond general-purpose agents.
On these two real tasks, Luna max with a GEAR-tuned harness completes requirements that Astra max with the general-purpose Codex agent misses. Watch the difference side by side.
CASE 02AutomationBench / Marketing
Featured snippet opportunities
Small model.
Serious results.
An optimized harness can change what an agent gets done. Explore the results reported in our open experiments.
Marketing · 100 public tasks
Objective completionTask pass rate also increased from 27% to 53%. Astra max with Codex scored 84.08% objective completion and 57% task pass rate.
Terminal-Bench 2.1
Task pass rateLuna’s reported task pass rate increased from 52.87% to 84.26%. These runs compare both a harness change and a reasoning-effort change.
How GEAR works.
Follow a real AutomationBench optimization: inspect failed runs, propose harness changes, evaluate candidates, and retain the versions that perform better.
Help more people discover GEAR.
Star on GitHub139