Category · Agent runtime

Memory layers for AI agents

Services that store what an agent learns about a user or a task and bring back the right parts later: facts, preferences, conversation summaries and knowledge graphs. Compared on recall quality, latency, what they keep and how you delete it.

Best memory layers for AI agents, the shortlist353 head-to-head comparisons

Capability keys memory.store · memory.search · memory.graph · memory.user · memory.delete · All tools

letme.dev/memory.store picks the top-graded tool in this list and says how to call it direct (how letme works).

26listings graded
6agent-ready (BB+)
52desk reviews by the panel
1accept x402
18 Nov 21:29last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Auth
Pricing
Status
26 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
17 Amazon Bedrock AgentCore MemoryAmazon Web Services · HTTP API Memory A 81.6 3.5 (4) $1 / GB
27 Basic MemoryBasic Memory LLC · MCP server Memory A 80.1 none $19 / mo
142 GraphicleKarLex AI, Inc. · MCP server Memory BB 74.4 3.8 (4) Free · OSS
198 ZepZep · HTTP API Memory BB 72.9 4.0 (2) $125 / mo
225 past.devRevo Inc. (doing business as Past Corp.) · HTTP API Memory BB 72.3 3.0 (4) $99 / mo
243 EverOSEvermind AI, Inc. · HTTP API Memory BB 71.9 none Freemium
358 AI MemoryFabio Akita · MCP server Memory B 68.8 3.5 (4) Free
460 Agent Platform Memory BankGoogle Cloud · HTTP API Memory B 66.8 none $0.0001 / 1k req
574 MemPalaceMemPalace (open-source project) · MCP server Memory B 64.5 none Free · OSS
616 TokenripQuintel, LLC · MCP server Memory B 63.5 3.8 (4) $20 / mo
617 LettaLetta · Agent harness Harnesses B 63.5 none $20 / mo
658 Memory (MCP reference server)MCP project (reference servers) · MCP server Databases B 62.6 2.5 (2) Free · OSS
689 HonchoPlastic Labs · HTTP API Memory B 62 3.0 (2) $0.001 / call x402
714 Supermemory API + MCPSupermemory · HTTP API Memory C 61.5 3.5 (2) $19 / mo
753 MemMachineMemVerge, Inc. · HTTP API Memory C 60.5 none Freemium
756 Egoist AI PassportEgoist Machines, Inc. · MCP server Memory C 60.4 3.8 (4) Freemium
869 Hy MemoryTencent (Hy team) · SDK + MCP Memory C 57.5 2.5 (4) Free · OSS
886 Context Mode EngineMKSF LTD · MCP server Memory C 57.1 3.5 (4) Freemium
951 claude-memAlex Newman · MCP server Memory C 55.9 none $30 / mo
988 TencentDB Agent MemoryTencent Cloud · HTTP API Memory C 54.6 none Free · OSS
1013 GraphitiZep · Agent framework Memory D 53.9 2.5 (2) Free · OSS
1103 LangMemLangChain · SDK + MCP Memory D 51.5 2.8 (4) Free · OSS
1142 CogneeCognee · Platform Memory D 49.9 3.0 (2) $5 / mo
1145 HindsightVectorize · HTTP API Memory D 49.7 3.0 (2) $0.05 / call
1218 MemoriMemori Labs Inc. · SDK + MCP Memory D 47 none Freemium
1307 Mem0 Platform + MCPMem0 · HTTP API Memory E 42.6 2.5 (2) Freemium

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

Indexed, not reviewed (63)

Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.

ListingKindWhat it doesWhy it's here
Achromat Machine Operational Memory
achromat.ai
MCP serverRecall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.vendor's own
adrkit decision memory
adrkit.dev
MCP serverDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.vendor's own
AiNecto
ainecto.com
MCP serverShared project memory for people and AI agents: documents, ERD, diagrams, boards, design mockups.vendor's own, widely used
BanditDB
banditdb.com
MCP serverPersistent decision memory for agents — learns which action works in which contextvendor's own
Bluet
bluet.dev
MCP serverProduct memory your agents read before they work: briefs, plan checks against decisions, debriefs.vendor's own
Bourdon
bourdon.ai
MCP serverRecognition-first cross-agent memory federation. One shared memory across all your agents.vendor's own
Citadel
citadeldb.dev
MCP serverEncrypted-first embedded database with vector search and agent memory, exposed as MCP toolsvendor's own
cluster-mcp
clusteragent.dev
MCP serverSelf-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.vendor's own
Compose MCP
smartmemory.ai
MCP serverTyped feature management for compose projects: roadmap, changelog, artifacts, journal.vendor's own
Counterparts
counterparts.ai
MCP serverLocal-first memory for AI: it interprets, forgets on purpose, and keeps a self across sessions.vendor's own, widely used
deerdawn
deerdawn.com
MCP serverAI session memory: the brief your AI reads before every session so no session starts cold.vendor's own
Docmancer
docmancer.dev
MCP serverLocal-only MCP server for source-attributed Markdown memory and documentation retrieval.vendor's own
Engram
engram.tools
MCP serverMemory for AI agent teams across tools, sessions, repositories, and teammates.vendor's own
engrava
sovantica.ai
MCP serverMindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.vendor's own
gjalla
gjalla.io
MCP serverSelf-curating shared memory that keeps your agents working like a high-performing teamvendor's own
Granoflow
granoflow.com
MCP serverConnect MCP-capable AI agents to local Granoflow tasks, reviews, cards, imports, and work memory.vendor's own
heropen — AI Agent Memory
heropen.net
MCP serverPersistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.vendor's own
HyperMarrow
qianshi.cool
MCP serverLocal-first long-term memory for AI coding agents. Stored on your own machine.vendor's own
in-memoria
pi22by7.me
MCP serverPersistent codebase intelligence that gives AI assistants memory across sessionsvendor's own
ITHZ MCP
ithz.dev
MCP serverLocal deterministic project memory for AI agents with context packs, gates and checkpoints.vendor's own
kage
kage-core.com
MCP serverVerified memory for coding agents: claims cited against code, stale withheld, savings receipts.vendor's own
Kawa Code
kawacode.ai
MCP serverTeam-aware memory: intent, decisions, real-time conflicts for AI coding assistants.vendor's own
Khwan
khwan.ai
MCP serverDurable AI memory: recall distilled facts in a later session or subagent, and remember new ones.vendor's own
Kognite
kognite.dev
MCP serverHosted agent memory: store, search, and recall facts across sessions from any MCP client.vendor's own
Koragraph
koragraph.in
MCP serverLocal multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.vendor's own
LBrain
lbrain.ai
MCP serverLocal-first agent memory. Source, date, bind/abstain. Permanent name: lbrain.ai/claim.htmlvendor's own
Lex
smartergpt.dev
MCP serverEpisodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.vendor's own
Lithtrix — Identity, Memory & Trust for AI Agents
lithtrix.ai
MCP serverIdentity, memory, trust, and swarm primitives for AI agents. MIRC base always free.vendor's own
Lodekeep
lodekeep.com
MCP serverMemory MCP server for Claude Code. Correct a fact and the old version stops being recalled.vendor's own
logic-server
nocturnus.ai
MCP serverAgent reasoning, memory, and token-optimized context for AI applications.vendor's own
MAGNEMO
magnemo.ai
MCP serverPersistent Memory for AI Agents, in plain local files. No network calls of its own.vendor's own
membase
membase.com
MCP serverLong-term memory for you and your AIs: search memories, read the profile, add facts and documents.vendor's own
MemCell
memcell.ai
MCP serverShared, persistent memory for AI agents: recall before acting, report outcomes to earn confidence.vendor's own
memento
runmemento.com
MCP serverLocal-first, LLM-agnostic memory layer for AI assistants.vendor's own
memgit
memgit.dev
MCP serverOne memory for Claude Code, Cursor and Codex on every machine, versioned with diff and rollbackvendor's own
MemoFS MCP Server
memofs.dev
MCP serverPersistent memory and virtual filesystem MCP server for AI agents.vendor's own
memory
cortex-mem.com
MCP serverShared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.vendor's own
memory-mcp
letta.com
MCP serverMCP server for AI memory management using Letta - Standard MCP formatvendor's own
MemoryLayer
memorylayer.in
MCP serverLocal-first persistent memory for AI agents, with reasoning and formal verification.vendor's own
Mint for Mac
dzgapp.com
MCP serverSmart disk and memory for you and your agents: space and RAM back through Mint, with undo.vendor's own
mnemodb
mnemodb.dev
MCP serverPersistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.vendor's own
modelbrain.net MCP server
modelbrain.net
MCP serverOne memory for Claude, ChatGPT and Cursor, kept on your computer. Optional sync, encrypted first.vendor's own
MyMemory
mymemory.dev
MCP serverLong-term memory for Claude, ChatGPT, Cursor: search, save and organize notes, links, docs, videos.vendor's own
Onadit
onadit.com
MCP serverMemory for your agents, kept on your Mac. Needs Onadit for Mac, from onadit.com/download.vendor's own, widely used
OnlyMCP
only-mcp.com
MCP serverSkills, agents and memory in the cloud, plus a gateway to your other MCP servers.vendor's own, widely used
P0 Agent Economy Index
x402-bazaar-rank.x402-bazaar-rank-worker.workers.dev
MCP serverPaid APIs for agents (x402 index) + SEC filings, wallet risk, OFAC, EVM reads, agent memory, newsvendor's own
Pastepile
pastepile.com
MCP serverDurable, versioned memory for AI assistants. Remote memory needs a Pastepile subscription.vendor's own
phototology.com MCP server
phototology.com
MCP serverPersistent memory for visual intelligence. A photo registry: analyze once, look up free after that.vendor's own
poppy
trags.ai
MCP serverDeveloper memory CLI and MCP server. Remember decisions, preferences, and lessons locally.vendor's own
RCLL
rcll.ai
MCP serverSelf-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.vendor's own
recall
clauderecall.com
MCP serverPersistent memory for Claude Code and Codex. Search and re-inject context from any session.vendor's own
Reverie
knowall.ai
MCP serverGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid searchvendor's own
Semurg agent memory
semurg.io
MCP serverSelf-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.vendor's own
SmartMemory
smartmemory.ai
MCP serverGraph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.vendor's own
stdio-proxy
mcp.undisk.app
MCP serverUndisk MCP: safe file memory for AI agents.vendor's own
Synap Memory
maximem.ai
MCP serverPersistent memory for AI agents — log and recall conversation context over MCP.vendor's own
Synchronex
synchronex.ai
MCP serverConnect any AI agent to your Synchronex workspace — portable memory, decisions, and workers.vendor's own
Trail
usetrail.dev
MCP serverIssue tracker and durable project memory for your coding agent, scoped to the folder you open.vendor's own
Tugra
tugra-ai.com
MCP serverProvenance-aware memory format for AI agents: every claim carries its source, age and boundary.vendor's own
wontopos.com MCP server
wontopos.com
MCP serverWontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.vendor's own

The first 60 of 63, most used first. All 63 are in this page's JSON twin and, with their facts, in /api/v1/indexed.json (category).

How we test this category

One user's history fed in over several sessions, then questions that need facts from early on, a changed preference and a deleted fact. We check what comes back, how fast, and whether the deletion sticks.

How the ranking works

Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.