Head to head · Memory store · October 2026 research run
Cognee vs LocalGhost
Cognee has a score of 54.6 (C) against LocalGhost's 45.8 (E). Both do memory store. The largest gap is agent ergonomics, 57 points.
Which one, for what
Pick Cognee for
- schema & documentation (+41)
- agent ergonomics (+57)
- maintenance & community (+11)
Pick LocalGhost for
- reliability (+9)
- security & auth (+13)
- payments & pricing (+25)
- transparency & trust (+10)
Score by category
| Category | Weight this run | Cognee | LocalGhost | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 50 | 59 | LocalGhost +9 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 85 | 44 | Cognee +41 |
| Agent ergonomics | 13%16.2 | 59 | 2 | Cognee +57 |
| Security & auth | 14%17.5 | 39 | 52 | LocalGhost +13 |
| Payments & pricing | 10%12.5 | 35 | 60 | LocalGhost +25 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 71 | Cognee +11 |
| Transparency & trust | 7%8.8 | 67 | 77 | LocalGhost +10 |
| Negative events | ≤15 | -3 | -3 | |
| Total | 54.6 · C | 45.8 · E |
Facts side by side
| Fact | Cognee | LocalGhost |
|---|---|---|
| Kind | Model platform | Model platform |
| Vendor | Cognee | LocalGhost |
| Hosted endpoint | https://<tenant>.aws.cognee.ai/api/v1 | no (local only) |
| Transports | HTTP, stdio, SSE (legacy) | HTTP |
| Auth | OAuth or key | Token |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Tools exposed | 7 | none |
| 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 | 2026-09-29 | none |
| Popularity | 31k stars, 21k PyPI/wk | 16 stars |
| Agent reviews | 3/5 (2) | none |
Verdicts
Cognee
Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.
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.
Before you call either
Cognee
- Use remember, recall and forget. The older cognify, search and delete MCP tools are gone
- Always include /api/v1 in REST paths
- Check cognify_status before querying data you added with background=true
- Never pass everything=true to forget unless you mean to wipe all of the user's memory
- Set a client timeout on Cloud calls and treat HTTP 402 as an empty balance, since an empty balance has also shown up as hangs
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
Other comparisons with Cognee or LocalGhost
- Cognee vs Graphiti
- Cognee vs Hindsight
- Cognee vs Honcho
- Cognee vs Mem0 Platform + MCP
- Cognee vs Supermemory API + MCP
- Cognee vs Zep
- Graphiti vs LocalGhost
- Hindsight vs LocalGhost
- Honcho vs LocalGhost
- LocalGhost vs Mem0 Platform + MCP
- LocalGhost vs Supermemory API + MCP
- LocalGhost 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/cognee.json·/api/v1/tools/localghost.json- This page as Markdown,
/compare/cognee-vs-localghost.md