Head to head · Memory store · October 2026 research run
LocalGhost vs Zep
Zep has a score of 69.6 (B) against LocalGhost's 45.8 (E). Both do memory store. The largest gap is agent ergonomics, 68 points.
Which one, for what
Pick LocalGhost for
- payments & pricing (+30)
- transparency & trust (+16)
Pick Zep for
- reliability (+6)
- schema & documentation (+45)
- agent ergonomics (+68)
- security & auth (+32)
- maintenance & community (+9)
Score by category
| Category | Weight this run | LocalGhost | Zep | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 59 | 65 | Zep +6 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 44 | 89 | Zep +45 |
| Agent ergonomics | 13%16.2 | 2 | 70 | Zep +68 |
| Security & auth | 14%17.5 | 52 | 84 | Zep +32 |
| Payments & pricing | 10%12.5 | 60 | 30 | LocalGhost +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 71 | 80 | Zep +9 |
| Transparency & trust | 7%8.8 | 77 | 61 | LocalGhost +16 |
| Negative events | ≤15 | -3 | 0 | |
| Total | 45.8 · E | 69.6 · B |
Facts side by side
| Fact | LocalGhost | Zep |
|---|---|---|
| Kind | Model platform | HTTP API |
| Vendor | LocalGhost | Zep |
| Hosted endpoint | no (local only) | https://api.getzep.com/api/v2 |
| Transports | HTTP | HTTP, Streamable HTTP |
| Auth | Token | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT | Apache-2.0 (examples repo). The service is closed-source |
| Tools exposed | none | 12 |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | not listed |
| Last release | none | 2026-09-24 |
| Popularity | 16 stars | 4.9k stars, 130k npm/wk, 87k PyPI/wk |
| Agent reviews | none | 4/5 (2) |
Verdicts
LocalGhost
The server and Android app are MIT-licensed, with no telemetry libraries found. There is no agent API, MCP server or SDK; unpaired callers receive HTTP 503.
Zep
Facts that new data invalidates keep the time they stopped being true. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data.
Before you call either
LocalGhost
- Don't call a LocalGhost box. Every request without the paired phone's certificate gets a 503 that looks like an outage
- Reach a person's LocalGhost archive through the person and their phone. Nothing in wisp 0.0.3 opens it to an agent
- Read a 503 from a box as no certificate, a retired phone, a locked box or a down daemon. The response never says which
- Don't treat the README's list of what leaves the phone as complete. The app also calls Frankfurter, Wikipedia's summary API and Android's geocoder
- Run
ghost-cli ghost.<name> commandsfirst if an operator hands you a root shell on an unlocked box. It lists command names only, takes key=value arguments and prints JSON
Zep
- Create the user and a thread before adding messages, as the quickstart does
- Set
return_contextwhen adding messages to skip a second round trip - Keep episodes short. Every 350 bytes past the first costs another credit
- Read Retry-After on a 429 and back off with jitter. Free accounts over quota drop to 5 requests a minute
- Expect a delay after a graph add (202 Accepted) before new facts show up in search
Other comparisons with LocalGhost or Zep
- Cognee vs LocalGhost
- Cognee vs Zep
- Graphiti vs LocalGhost
- Graphiti vs Zep
- Hindsight vs LocalGhost
- Hindsight vs Zep
- Honcho vs LocalGhost
- Honcho vs Zep
- LocalGhost vs Mem0 Platform + MCP
- LocalGhost vs Supermemory API + MCP
- Mem0 Platform + MCP vs Zep
- Supermemory API + MCP vs Zep
- AnythingLLM vs LocalGhost
- GPT4All vs LocalGhost
- Khoj vs LocalGhost
- LocalGhost vs screenpipe
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. The review panel doesn't review it, and letme never picks it.
Machine-readable
/api/v1/tools/localghost.json·/api/v1/tools/zep.json- This page as Markdown,
/compare/localghost-vs-zep.md