We independently measure the tools AI agents use and publish what each one actually adds.
Agentic Memory Index v0.1 · Aug 2026
Highlights
Accuracy, cost, and speed for every tool, measured the same way.
Check your own setup
Your agent already knows which tools you run. Paste one prompt and it checks that setup against the measured data, then tells you in plain words what would actually help.
Which memory tool is right for your agents?
No tool wins everything: match each tool's strengths to the questions your agents actually ask.
Correct Answers by Task Typei
From direct recall to synthesis, each tool has its strengths.
— Claude Code built-in memoryClaude Code memory
57%
Direct RecallUpdated FactsThread GrowthSynthesisLong TermFalse memory check
Failure Attributioni
Know how each tool tends to fail before your agent depends on it.
— Claude Code built-in memoryClaude Code memory
39.5%
Incorrect AnswerQuestion Not AddressedOutdated AnswerFabricated Memory
Rankings and retention
Every tool's score, and whether what it stores survives.
Agentic Memory Index Leaderboardi
Every tool's score, cost, and speed in one table.
Long-term retentioni
How well early facts survive: probed at five checkpoints across 56 working sessions.
Agentic Search Index
Nine web search tools measured on a shared bank of live research questions.
Speed
One-time setup, indexing lag, and per-operation latency.
Speed
Onboarding, readiness, and store-session times for every tool.
Where retrieval time goesi
The average answer, second by second.
— Claude Code built-in memoryClaude Code memory
2.1s
PlanLookupsErrors & retriesReading resultsComposing answers
Let Your Agent Access This Data
Every number on this page is live over x402: an agent pays 0.035 USDC and gets the data with no account and no API key. A standard subscription based API is coming soon.
Pricing and cost
What the tools charge, and what successful answers actually cost.
Pricing at a glance
What each tool costs to start, from list pricing.
List prices as of Jul 27, 2026.
Cost Breakdowni
Per 1,000 successful answers: agent token spend, the entry paid tier amortized at its capacity, and embeddings where billed separately.
— Claude Code built-in memoryClaude Code memory
$426.90
Agent TokensSubscriptionEmbeddings