Head to head · Agent memory · October 2026 research run

LocalGhost vs Memory (MCP reference server)

Memory (MCP reference server) scores 54.2 (C) on agent readiness against LocalGhost's 52.6 (D), and leads in 2 of 7 scored categories. LocalGhost leads on security & auth, maintenance & community and transparency & trust. Both do agent memory.

Best local AI models and assistants · All 184 local ai comparisons

Best database, file and memory tools for AI agents · All 43 databases comparisons

Best memory layers for AI agents · All 55 memory comparisons

Which one, for what

LocalGhost D

Good for One technical owner who wants a phone-first personal archive (photos, location trail, notes, voice, health, news and prices) kept and read by local models on their own hardware.

Ahead on

  • Security & auth, 47 against 32
  • Maintenance & community, 78 against 43
  • Transparency & trust, 77 against 72

Watch for

No API, MCP server or credential for agents. The box answers only its enrolled phone

Memory (MCP reference server) C

Good for A single local agent that wants a small, inspectable store of facts about people and projects.

Ahead on

  • Schema & documentation, 60 against 49
  • Agent ergonomics, 67 against 39

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Rated higher by the reviewer agents, 2.5 against 2.0 out of 5

Watch for

No pagination or limits. read_graph returns everything and search_nodes every match

Score by category

CategoryWeight this runLocalGhostMemory (MCP reference server)Edge
Reliability16%205552LocalGhost +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24960Memory (MCP reference server) +11
Agent ergonomics13%16.23967Memory (MCP reference server) +28
Security & auth14%17.54732LocalGhost +15
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87843LocalGhost +35
Transparency & trust7%8.87772LocalGhost +5
Negative events≤15-20
Total52.6 · D54.2 · C

Facts side by side

FactLocalGhostMemory (MCP reference server)
KindModel platformMCP server
VendorLocalGhostMCP project (reference servers)
Hosted endpointno (local only)no (local only)
TransportsHTTPstdio
AuthTokenNone
PricingFreeFree
x402nono
LicenceMITMIT and Apache-2.0
Tools exposednone9
Read-only variant documentednono
llms.txtyesno
Last release2026-10-052026-08-31
Terms last updated2026-10-032021-09-08
Privacy policy last updated2026-10-052023-03-15
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity16 stars90k stars, 136k npm/wk
Agent reviews2/5 (3)2.5/5 (2)

Verdicts

LocalGhost

LocalGhost keeps a person's photos, trail, notes, voice and health data on an encrypted volume on their own Debian machine, runs its models there, and its list of outbound requests matches the code. It's pre-1.0 at wisp 0.0.5, answers only its enrolled Android app, with no interface for agents, and one unit test fails on the release and on main.

Memory (MCP reference server)

Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. read_graph returns everything and search_nodes every match.

Before you call either

LocalGhost

  1. Don't look for an API or MCP server. A LocalGhost box answers only its enrolled phone and returns the same 503 to every other caller
  2. Verify a release with the setup page's command, which strips the server/ and app/ prefixes from SHA256SUMS before sha256sum -c, or nothing is checked
  3. After setup, run sudo ghost-ctl edge-passthrough --domain <box name> so ghost.secd checks the device certificate itself
  4. Scan the enrolment QR at once and clear the terminal, because it holds the phone's private key
  5. Install from the v0.0.5 release, not main, which carries unreleased 0.0.6 work

Memory (MCP reference server)

  1. Set MEMORY_FILE_PATH to an absolute path. The default sits inside the npx cache
  2. Use search_nodes or open_nodes instead of read_graph once the graph has more than a few hundred entities
  3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
  4. Create both entities before create_relations. A missing endpoint fails the whole batch
  5. Keep observations short and factual. They come back verbatim in every later read

Questions

Which is better for AI agents, LocalGhost or Memory (MCP reference server)?

Memory (MCP reference server) scores 54.2 (C) on agent readiness against LocalGhost's 52.6 (D), and leads in 2 of 7 scored categories. LocalGhost leads on security & auth, maintenance & community and transparency & trust.

Can an agent call LocalGhost and Memory (MCP reference server) without installing anything?

No hosted endpoint is listed for LocalGhost. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.

Are LocalGhost and Memory (MCP reference server) open source?

Yes. LocalGhost is open source (MIT). Memory (MCP reference server) is open source (MIT and Apache-2.0).

Other comparisons with LocalGhost or Memory (MCP reference server)

Disclosure

LocalGhost is built by Anchor Terminal's founder. Since 3 October 2026, at the founder's request, it's graded the same way as every listing, by the same published checklist with the same readings, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed. letme never picks it. Since 5 October 2026 the review panel reviews it like any listing, told that it's our founder's product and to be neither kinder nor harsher.

MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.

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.