We present TapeAgents, an agent framework that leverages a structured, replayable log (tape) of the agent session to facilitate all stages of the LLM Agent development lifecycle. In TapeAgents, the agent reasons by processing the tape and the LLM output to produce new thought and action steps and append them to the tape. The environment then reacts to the agent’s actions by likewise appending observation steps to the tape. By virtue of this tape-centred design, TapeAgents can provide AI practitioners with holistic end-to-end support. At the development stage, tapes facilitate session persistence, agent audit, and step-by-step debugging. Post-deployment, one can reuse tapes for evaluation, fine-tuning, and prompt-tuning; crucially, one can adapt tapes from other agents or use revised historical tapes. In this report, we explain the TapeAgent design in detail. We demonstrate possible applications of TapeAgents with several concrete examples of building and optimizing agents using diverse paradigms. We present tooling prototypes and report a case study where we use TapeAgents to finetune a Llama-3.1-8B form-filling assistant to perform as well as GPT-4o while being orders of magnitude cheaper. We compare TapeAgents to prior agent frameworks and find that TapeAgents is the first one that helps the practitioner to build, debug, serve, and optimize their agent.