A Markdown wiki outscored every AI agent memory product we benchmarked

See how much smarter your AI could be by adding tools We independently measure the tools AI agents use and publish what each one actually adds. Personalized Tool Guidance See Agentic Search Index → Agentic Memory Indexi Rank By: Methodology Agentic Memory Index v0.1 · Aug 2026 Highlights Accuracy, cost, and speed for every tool, measured the same way. Agentic Memory Indexi The overall score: how often each tool finds the right answer. Claude Code built-in memory 67.7 Costi USD per 1,000 successful answers Claude Code built-in memory $426.90 Answer speedi How long an answer takes end to end, same agent model on every tool. Claude Code built-in memory 2.1s 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. Get personalized tool guidance → 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. Rank By: 1 Karpathy Wiki 98% 2 Mitosis Cortex 96% 3 gbrain 93% 4 Mem0 91% 5 Hyperspell 90% 6 Anthropic Memory 81% 7 Zep 79% 8 Supermemory 75% — 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. Rank By: 1 Karpathy Wiki 1.0% 2 Mitosis Cortex 4.0% 2 Mem0 4.0% 4 Zep 5.0% 5 gbrain 6.5% 6 Hyperspell 7.0% 7 Anthropic Memory 23.5% 8 Supermemory 33.0% — 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. #ServiceIndex ↓Cost / 1kLookups / sessionLookups 1 Karpathy Wiki 98.5 $568.93 1.6 2 Mitosis Cortex 96.9 $418.40 5.1 3 gbrain 92.9 $471.40 5.3 4 Hyperspell 92.4 $429.71 6.8 5 Mem0 92.3 $341.42 5.1 6 Anthropic Memory 84.0 $419.45 8.4 7 Supermemory 77.1 $519.04 5.7 8 Zep 75.1 $394.75 5.1 — Claude Code built-in memoryClaude Code memory 67.7 $426.90 — 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. See the search index → Speed One-time setup, indexing lag, and per-operation latency. Speed Onboarding, readiness, and store-session times for every tool. ToolOnboard ↑Time to readyTime to store Anthropic Memory 1.1 min local 56.0s Mem0 1.1 min 2.9s 41.0s Karpathy Wiki 1.4 min local 62.0s Hyperspell 1.9 min 0.45s 41.0s gbrain 3.2 min local 99.0s Mitosis Cortex 5.2 min 0.40s 55.0s Supermemory 5.2 min 4.6s 57.0s Zep 9.1 min 162.7s 41.0s Claude Code built-in memoryClaude Code memory — local 25.0s Where retrieval time goesi The average answer, second by second. Rank By: 1 Karpathy Wiki 2.7s 2 Zep 4.3s 3 Mitosis Cortex 4.4s 4 Mem0 5.3s 5 Supermemory 5.5s 6 Hyperspell 7.9s 7 Anthropic Memory 9.0s 8 gbrain 10.3s — 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. Get data with one prompt → 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. ToolFree tierStarting atOpen source Karpathy Wiki Always $0 Open method Mitosis Cortex 7-day trial $7.99/mo Closed gbrain Pay for embeddings $0 Yes Hyperspell No cap hit at 200+ Not Listed Closed Mem0 ~550 answers/mo $19/mo Core is Anthropic Memory Always $0 Yes Supermemory ~800 answers/mo $19/mo Yes Zep ~950 answers/mo $125/mo Engine (Graphiti) is Claude Code built-in memoryClaude Code memory Included with Claude Code $0 Bundled 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. Rank By: 1 Mem0 $341.42 2 Zep $394.75 3 Mitosis Cortex $418.40 4 Anthropic Memory $419.45 — Claude Code built-in memoryClaude Code memory $426.90 5 Hyperspell $429.71 6 gbrain $471.40 7 Supermemory $519.04 8 Karpathy Wiki $568.93 Agent TokensSubscriptionEmbeddings