Coding AgentsOpen SourceSandboxingAgent WorkflowDeveloper ExperienceOpenHandsEvalsAgent PatternBenchmarks
OpenHands
AI software development agent
OpenHands is an open-source AI software development agent for coding and repository-level task execution.
Recent stories
2 linked stories
newsPRIMARY2026-03-23
OpenHands benchmarks EvoClaw and caps continuous-evolution scores at 38.03%
OpenHands introduced EvoClaw, a benchmark that reconstructs milestone DAGs from repo history to test continuous software evolution instead of isolated tasks. The first results show agents can clear single tasks yet still collapse under regressions and technical debt over longer runs.
workflowPRIMARY2026-03-20
OpenHands compares 3 skill tasks and finds some reduce agent pass rates
OpenHands published a skill-eval recipe with bounded tasks, deterministic verifiers, and no-skill baselines, then showed some skills speed agents up while others make them brittle. Teams shipping skill libraries should measure them per task and model before rollout.