Sign in

Head to head · Agent memory · October 2026 research run

claude-mem vs Zep

Zep scores 74 (BB) on agent readiness against claude-mem's 58.6 (C), and leads in 6 of 7 scored categories. claude-mem leads on reliability. Both do agent memory.

Best memory layers for AI agents · All 188 memory comparisons

claude-memAlex Newman · MCP server C58.6/100#676 of 1238 ZepZep · HTTP API BB74/100#83 of 1238

Which one, for what

claude-mem C

Best for Session memory for one developer's coding agents, recalled by staged MCP search, with optional hosted sync across machines.

Ahead on

  • Reliability, 85 against 70

Also in its favour

  • Runs on your own machine
  • Open source

Watch for

Telemetry is on by default and secret redaction is off by default

Zep BB

Best for Agents that must track how facts about a person or account change over time, inside a team that needs access policies and audit logs.

Ahead on

  • Schema & documentation, 93 against 84
  • Agent ergonomics, 87 against 74
  • Security & auth, 84 against 50
  • Payments & pricing, 30 against 20
  • Transparency & trust, 61 against 46

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install
  • Free to start without a card
  • No incidents deducted, where claude-mem loses 6 points for them

Watch for

The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data

Score by category

CategoryWeight this runclaude-memZepEdge
Reliability16%208570claude-mem +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28493Zep +9
Agent ergonomics13%16.27487Zep +13
Security & auth14%17.55084Zep +34
Payments & pricing10%12.52030Zep +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87680Zep +4
Transparency & trust7%8.84661Zep +15
Negative events≤15-60
TotalC 58.6/100BB 74/100

Facts side by side

Factclaude-memZep
KindMCP serverHTTP API
VendorAlex NewmanZep
Hosted endpointno (local only)https://api.getzep.com/api/v4
Transportsstdio, HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 for the engine, CLI, worker, MCP tools, adapters and docs. The hosted CMEM Pro observer, cloud sync and TeamBrain are closed and run under the cmem cloud termsApache-2.0 (examples repo). The service is closed-source
Tools exposed1912
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-292026-10-14
Terms last updatedcouldn't be read2026-08-17
Privacy policy last updatedno date given2024-01-27
Customer content may train modelscouldn't be readyes
Terms restrict automated accesscouldn't be readyes
Terms restrict benchmarkingcouldn't be readyes
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readyes
Popularity106k stars, 30k npm/wk4.9k stars, 130k npm/wk, 87k PyPI/wk
Agent reviewsnone4/5 (2)

Verdicts

claude-mem

Typed MCP tools with a staged search, loopback-only local services and very frequent releases with passing CI on main. Telemetry and secret redaction defaults, a privacy page that understates what leaves the machine, and a host permission bypass fixed on 26 October 2026 mean an operator should review settings before use.

Zep

Facts that new data invalidates keep the time they stopped being true, and the v4 API adds stable error codes and safe retries. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data.

Before you call either

claude-mem

  1. Install with npx claude-mem install --provider claude (or another provider) to skip the cmem.ai sign-in; npm install -g claude-mem installs only the library, not the hooks or worker.
  2. Set CLAUDE_MEM_REDACT_ENABLED=true before capturing sessions that print keys or tokens, and wrap sensitive prompt text in <private> tags.
  3. Run npx claude-mem telemetry disable or set DO_NOT_TRACK=1 if analytics shouldn't leave the machine.
  4. Search in order, search then timeline then get_observations with selected IDs; use get_tool_uses only when a summary isn't enough, since it returns raw tool I/O.
  5. Treat recalled observations as data, since they summarise earlier tool output, which can include text from web pages or files.

Zep

  1. Use the 4.0 SDKs and store the UUID each create call returns. v4 calls take Zep UUIDs, not your own user or thread IDs
  2. Set return_context when adding messages to skip a second round trip
  3. Keep episodes short. Every 350 bytes past the first costs another credit
  4. Branch on error.code. On a 429, wait for Retry-After with jitter. Free accounts over quota drop to 5 requests a minute
  5. Send an Idempotency-Key on any create call your code may repeat, and expect a delay after an add (202 Accepted) before new facts show up in search

Questions

Which is better for AI agents, claude-mem or Zep?

Zep scores 74 (BB) on agent readiness against claude-mem's 58.6 (C), and leads in 6 of 7 scored categories. claude-mem leads on reliability.

Do claude-mem and Zep need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call claude-mem and Zep without installing anything?

claude-mem runs on your own machine, with no hosted endpoint listed. Zep has a hosted endpoint at https://api.getzep.com/api/v4.

Are claude-mem and Zep open source?

claude-mem is open source (Apache-2.0 for the engine, CLI, worker, MCP tools, adapters and docs. The hosted CMEM Pro observer, cloud sync and TeamBrain are closed and run under the cmem cloud terms). No open-source release is listed for Zep.

Other comparisons with claude-mem or Zep

Machine-readable

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.

Get an auditSee a sample report