Background Induction of labour is carried out for a variety of indications and using a range of pharmacological, mechanical and other methods. For women at low risk, some methods of induction of labour may be suitable for use in outpatient settings. Objectives To examine pharmacological and mechanical interventions to induce labour in outpatient settings in terms of feasibility, effectiveness, maternal satisfaction, healthcare costs and, where information is available, safety. The review complements existing reviews on labour induction examining effectiveness and safety. Search strategy We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (December 2009) and reference lists of retrieved studies. Selection criteria We included randomised controlled trials examining outpatient cervical ripening or induction of labour with pharmacological agents or mechanical methods. Data collection and analysis Two authors independently extracted data and assessed eligible papers for risk of bias. We checked all data after entry into review manager software. Main results We included 28 studies with 2616 women examining different methods of induction of labour where women received treatment at home or were sent home after initial treatment and monitoring in hospital. Studies examined vaginal and intracervical PGE(2), vaginal and oral misoprostol, isosorbide mononitrate, mifepristone, oestrogens, and acupuncture. Overall, the results demonstrate that outpatient induction of labour is feasible and that important adverse events are rare. There was no strong evidence that agents used to induce labour in outpatient settings had an impact (positive or negative) on maternal or neonatal health. There was some evidence that, compared to placebo or no treatment, induction agents reduced the need for further interventions to induce labour, and shortened the interval from intervention to birth. We were unable to pool results on outcomes relating to progress in labour as studies tended to measure a very broad range of outcomes. There was no evidence that induction agents increased interventions in labour such as operative deliveries. Only two studies provided information on women's views about the induction process, and overall there was very little information on the costs to health service providers of different methods of labour induction in outpatient settings. Authors' conclusions Induction of labour in outpatient settings appears feasible. We do not have sufficient evidence to know which induction methods are preferred by women, or the interventions that are most effective and safe to use in outpatient settings.