B'
Bench'd
langchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvalverifiedstate 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalLetta 88.4 on LongMemEval3 systems independently scored36 systems indexedlangchain-memory 0.0 on LongMemEvalcognee 0.0 on LongMemEvalmem0-local 0.0 on LongMemEvalllamaindex-memory 0.0 on LongMemEvalllm-baseline 0.0 on LongMemEvalverifiedstate 0.0 on LongMemEvallangchain-memory 0.0 on LongMemEvalLetta 88.4 on LongMemEval3 systems independently scored36 systems indexed

Letta

Listed
Letta IncWebsiteGitHub(38.2k)DocsLast tested May 8, 2026
MCP Endpoint:https://api.letta.com/mcp/v1

Stateful LLM agent framework (formerly MemGPT) with built-in memory management, tool use, and multi-step reasoning. Self-editing memory architecture enables unbounded context.

This system hasn't been benchmarked by Bench'd yet.

Listed systems are indexed but not yet scored. Check back soon.

Command Palette

Search for a command to run...