Keep Claude Code, Cursor, Windsurf, and OpenCode as your agent runtime while adding 12.9 ms deterministic memory (100% LongMemEval vs. Letta's 74.0% LOCOMO).
| Criterion | Memoria | Letta (MemGPT) |
|---|---|---|
| LongMemEval Accuracy (500 q) | 100.0% (500 / 500) | 74.0% (LOCOMO) |
| Multilingual / Hebrew LongMemEval | 100.0% (102 / 102 · 98%+ enterprise bar · 15 languages) | LLM prompt dependent |
| Recall & Code Query Latency | <20ms (12.9 ms avg) | 500–2,500 ms (agent tool-call loop) |
| LLM Token Cost per Write | 0 tokens ($0) | Full LLM agent turn per memory edit |
| Belief Revision on State Change | Automatic Supersedes revision | Agent self-edits markdown blocks |
| IDE & MCP Ecosystem | 15 AI clients auto-configured · 30 MCP tools | Requires adopting Letta runtime/ADE |
| 1-Click Migration Importer | CLAUDE.md, .cursorrules, Mem0 JSON, ChatGPT & Claude | Custom script required |
| Pricing | $0 Free (1,000 calls) · $19 / $79 / $299 mo | $20–$200/mo hosted runtime |
Choose Letta if you want an all-in-one stateful agent server that replaces your existing orchestration framework.
Choose Memoria when you want to keep your existing IDE or agent framework (Claude Code, Cursor, Windsurf, OpenCode, Codex, VS Code, Zed, or custom Python/TS agents) and plug in 30 deterministic MCP tools in one command.
1. Create your free Memoria account (1,000 API calls & memories included).
2. Open Memory Explorer on /account and paste your Letta (MemGPT) JSON export, CLAUDE.md, or .cursorrules.
3. Run the one-line installer below to connect all 15 AI coding clients:
curl -fsSL https://memoria.kolivri.com/downloads/install.sh | MEMORIA_KEY=mem_dev_your_key_here bash