The deciding difference is operational: Letta can run on infrastructure you control, Claude Agent SDK cannot. If that constraint is real for you, it settles the choice before anything else is considered.
The Claude Code loop as a library, for agents that are not about code.
Same harness as Claude Code, but you own the entrypoint and the tool surface.
Stateful agent server where memory is the primary abstraction.
| Claude Agent SDK | Letta | |
|---|---|---|
| Licence | Proprietary | Open source |
| Pricing | usage based | freemium |
| Self-hostable | No | Yes |
| Languages | TypeScript, Python | Python, TypeScript |
| Install | npm install @anthropic-ai/claude-agent-sdk | pip install letta |
| Keys required | ANTHROPIC_API_KEY | None |
The deciding difference is operational: Letta can run on infrastructure you control, Claude Agent SDK cannot. If that constraint is real for you, it settles the choice before anything else is considered. Claude Agent SDK: The Claude Code loop as a library, for agents that are not about code. Letta: Stateful agent server where memory is the primary abstraction.
Claude Agent SDK is a hosted service only. Letta can run on your own infrastructure.
Claude Agent SDK is proprietary (usage based). Letta is open source (freemium).
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/compare/claude-agent-sdk-vs-letta