Source: Rearchitecting Letta's Agent Loop (Letta, 2025)
Letta's letta_v1_agent drops MemGPT heartbeats, the send_message tool and tool-argument inner thoughts in favour of native reasoning and native multi-step tool use.
Contents
- What: vendor engineering blog post
- Publisher: Letta
- Date: 14 October 2025
- Original: letta.com/blog/letta-v1-agent
Summary
Explains why Letta replaced the MemGPT-style agent loop. MemGPT was designed for models that could not reliably chain tools or reason natively, so it simulated both with tool arguments. Frontier models are now post-trained for multi-step tool use and self-termination, so Letta’s new default loop lets the model drive.
Key claims
- Removed: the
request_heartbeatargument for chaining tool calls; thesend_messagetool (the model’s plain assistant message is now the reply); thethinkingargument for inner thoughts (replaced by native reasoning). - Rationale: keeping agents “in-distribution” for models such as GPT-5 and Claude Sonnet 4.5 significantly improves performance.
- Native reasoning supported (OpenAI via the Responses API; encrypted reasoning handled across providers); tool calling is no longer required to connect a model.
- Trade-offs: non-reasoning models produce no reasoning and prompted reasoning is unsupported; encrypted reasoning cannot be edited or moved between models; tool rules cannot constrain assistant messages; sleep-time style independent runs need custom prompting.
- The original MemGPT architecture remains supported; V1 is recommended for current reasoning models.