Legacy Agent Architectures
This documentation covers legacy agent architectures.
For new projects, you should not specify an agent_type parameter. Letta uses the current architecture by default, which provides the best performance with modern reasoning models like GPT-o1 and Claude Sonnet 4.5.
Current Architecture
When you create an agent in Letta today, it uses our latest agent architecture optimized for:
- Full support for native reasoning (via Responses API)
- Compatibility with any LLM (tool calling not required)
- Simpler base system prompt
- Better performance on frontier models
You don’t need to specify an architecture. Just create an agent:
Why Legacy Architectures Exist
Letta evolved from the MemGPT research project. Early versions used specific agent architectures with names like:
memgpt_agent- Original MemGPT paper implementationmemgpt_v2_agent- Iteration with sleep-time compute and file toolsletta_v1_agent- First transition away from MemGPT naming
These names are confusing because:
- The naming progression (memgpt → memgpt_v2 → letta_v1) is non-standard
- LLMs trained on these docs get confused about which to recommend
- New users shouldn’t need to think about architecture choices
Do I Need to Migrate?
If you created your agents recently (after October 2024): You’re likely already on the current architecture. No action needed.
If you have existing agents with agent_type specified: Your agents will continue to work, but we recommend migrating to benefit from:
- Better performance on new models
- Native reasoning support
- Simplified prompting
Legacy Architecture Types
If you’re working with older agents or need to understand the differences:
Learn more about each legacy type →
Getting Help
- Discord confusion? Share your agent setup in #dev-help
- Need to migrate? Follow our migration guide
- Building something new? Start with our quickstart (no architecture choice needed!)