Real runs, graded objectively. Pick a benchmark to see the conclusion first — then the evidence. The same discipline applies to every claim MemoryLayer makes: verify before you believe it.
shadcn-ui/ui · 72% cheaper overall · 6 questions
Same model, same questions, same repo — only the tools differ. fs_list / fs_grep / fs_read vs a single memory_weave call over 750 pre-ingested symbols. Tokens from usage.input_tokens, both sides prompt-cached.
Token comparison
| Type | Question | fs tools | memory_weave | Δ cost |
|---|---|---|---|---|
| literal | Where is the Button component defined and what library powers its variants? | 3 turns5,573 tok$0.0836 | 2 turns4,803 tok$0.072 | −14% |
| literal | How is the Dialog component structured and what primitive does it wrap? | 3 turns12,452 tok$0.1868 | 2 turns5,028 tok$0.0754 | −60% |
| literal | Which file defines the cn class-name utility and what does it combine? | 3 turns3,996 tok$0.0599 | 2 turns5,037 tok$0.0756 | +26% |
| semantic | Which components in this repo support keyboard shortcuts or display key bindings? | 3 turns13,114 tok$0.1967 | 2 turns5,009 tok$0.0751 | −62% |
| semantic | How does this codebase express form validation and error messages? | 6 turns54,670 tok$0.8201 | 2 turns4,680 tok$0.0702 | −91% |
| semantic | What components are available for visualizing tabular data or charts? | 3 turns13,460 tok$0.2019 | 2 turns4,611 tok$0.0692 | −66% |
Model: claude-opus-4-8. Tokens from Anthropic API usage.input_tokens (exact, real agentic loop). Repo: shadcn-ui/ui (750 symbols). $/Q at Opus list pricing ($15/M input).
With memory_weave as the entry point and prompt caching enabled on the client, the realistic average is 72% cheaper than the same Opus loop with fs tools (N=1average). The savings over multi-tool MemoryLayer are unconditional; the rest comes from caching, which is one line in any Anthropic SDK integration. And that's before counting cross-session memory, where fs tools have nothing to offer.
Add persistent memory in 5 minutes.
One namespace — every agent, chat, and teammate.