AI memory comparison
Tephra vs Gemini memory
Gemini memory is a personalization feature inside Google's own apps. It is free on a personal Google Account, captures automatically, and reaches into Gmail, Photos and Calendar through Connected Apps. It also does not leave Gemini: there is no MCP server and no way to carry that memory to another assistant. Tephra is the opposite trade - nothing is captured for you, but what is saved is reachable from every AI app you connect.
Sources read and prices checked 2026-10-10.
Obsidian Metrics makes Tephra and Tracker, the two products this page compares against others. This page is written by the maker of one of the products compared, so read the competitor columns against their own pages, linked below each table. Competitor facts come only from the vendor pages listed under Sources, read on the date shown above; vendors change plans and prices without notice. We are not affiliated with any company named here, and all product names belong to their owners.
Tephra and Gemini memory side by side
| Feature | Tephra | Gemini memory |
|---|---|---|
| What it is | A hosted memory your connected AI apps share: they recall from it and write to it over MCP or REST. | A personalization feature inside Google's Gemini apps. It can draw on the memory of your past Gemini chats and on Connected Apps, with saved facts branded Personal Intelligence. [1] [2] |
| Entry price | Tephra needs a paid plan: Premium at $19 a month in the Obsidian Metrics Skool community or $29 a month direct, or a $399 one-time seat. No free tier. | Memory of past Gemini chats needs only a personal Google Account with Keep Activity on, at no stated extra cost. Managing saved facts requires a paid Google AI plan. We did not record a Google AI plan price because the figures are rendered in the browser and we could not read them from the page itself. [1] [3] |
| How usage is limited | No usage metering. There are only abuse limits: 60 requests a minute per key and 120 a minute per member. | Consumer subscription tiers rather than metered memory, but with hard eligibility gates: 18 or over, a personal Google Account only, and saved facts are US-only. Google states the feature is not available on work, school or supervised accounts. [1] [3] |
| Reach across AI apps | One memory for every AI you connect, led by OAuth sign-in: the Connect page has steps for Claude (web, Desktop, mobile), ChatGPT, VS Code Copilot, Cursor, Claude Code, Gemini CLI, Windsurf, Zed, Mistral Le Chat and Perplexity, plus generic steps for any other MCP app, and a personal key as a fallback, plus REST. AI tools that support neither MCP nor REST calls cannot connect. Tephra's OAuth discovery endpoints were verified live on 2026-10-10. | None. Google scopes it to the Gemini mobile and web apps, Gemini in Chrome and Gemini on a smartwatch. There is no MCP server and no third-party client; its reach runs inward, through Connected Apps, instead. [1] |
| Seeing and correcting what is stored | A member can view memories, edit or delete them, read edit history, contest a memory, export their own data (app session), and revoke any AI key with an activity log. | Still the weakest here, by Google's own description. There is an on/off switch and an editable instructions list, and you can ask Gemini to remember a fact or correct a wrong one conversationally - Google says "Gemini will update its memory based on your correction". But there is no list of remembered facts to read: to delete something Gemini remembered, Google says to delete all chats containing it, and to disconnect the app as well if it came from a connected app. Google also warns that deletion can lag, that connected-app deletions "may not be affected until days later", and that instructions to forget or avoid a topic "doesn't always work perfectly". [3] [1] |
| Hosting and self-hosting | Hosted service run by Obsidian Metrics. Self-hosting is not part of the product. We make no encryption-at-rest or compliance-certification claim. | Cloud only and closed, as a consumer feature of Google's own apps. No self-hosting and no data-residency option described. [1] |
| How memories get in | The connected AI writes them by calling a remember tool. Tephra does not capture chats automatically and has no Gmail, Slack or Drive connectors. You can upload text, markdown, JSON, XML and text-layer PDF files. | Both, and broadly. Gemini can learn from your chats automatically when Keep Activity is on, you can tell it to remember something explicitly, and Connected Apps let it draw on your Google apps. [1] [3] |
Where Gemini memory is better
- Gemini memory. Is already on, already paid for, and already attached to the user's real life through Connected Apps, so Gmail, Photos and Calendar context arrives with no integration work at all - against which Tephra knows only what an AI typed into its save tool. Memory of past chats costs nothing on a personal Google Account, capture is automatic, correction happens conversationally inside the chat, and it needs no setup on phone, web, Chrome or a watch. [1] [3]
Choose Gemini memory if: You use Gemini and want memory that already knows your life through your Google apps, at no extra cost, with no setup. For a consumer that context is not something Tephra can match, because Tephra has no connectors at all.
Where Tephra is better
- Connected AI apps read and write the same memory directly, rather than moving it between apps by pasting text. Claude's import and export, for example, works by pasted text, and its import path is marked experimental.
- A flat price with no usage metering, instead of credits or request quotas.
- A shared library that Tephra grows every hour from public research and regulatory sources, included with the product. We did not find a competitor that bundles one; that is a qualitative check, not an exhaustive market survey.
- Recall in the app tells you which related memories it did not load and how complete the answer looks.
Choose Tephra if: You use more than one AI assistant, or you want to see and correct a list of what is stored. Google's own help pages say there is no list of remembered facts to edit: to remove one you delete the chats that contain it, deletion can lag, and telling Gemini to forget a topic "doesn't always work perfectly". Gemini memory is also unavailable on work, school and supervised accounts, and saved facts are US-only and 18+.
Where Tephra falls short
- Tephra has no free tier and no self-hosted option.
- The MCP tools return ranked records only. The completeness alert is shown in the app, not through MCP.
- No automatic chat capture, and no connectors to Gmail, Slack or Drive.
- No image or audio ingest, and no OCR for scanned PDFs.
- Stale-fact handling is partial.
- No published, vendor-comparable benchmark, and no accuracy lead we can defend.
What we have and have not measured
On 50 held-out LongMemEval-S questions never used in Tephra development, Tephra answered 39 of 50 correctly (78%, 95% confidence interval 65-87%) with a gpt-4o-mini reader, and every evidence session was in its top 10 results for 46 of 46 answerable questions.
Method: LongMemEval-S cleaned, stratified 100-question subset; gpt-4o-mini reader over top-10 retrieved items; official GPT-4o judge prompt; one run, 2026-10-08; held-out questions are the 50 never used in earlier Tephra tuning; competitors run locally from open source under the same harness.
In that same-harness run, none of Tephra's leads over the other systems tested was statistically significant after correcting for multiple comparisons, and its margin over a plain keyword-search baseline was not significant either. We do not claim Tephra is the most accurate memory. We did not benchmark Supermemory, Zep, ChatGPT memory or Claude memory, and we do not compare ourselves with any vendor's self-reported numbers.
Frequently asked
Is Gemini memory free?
Memory of past Gemini chats requires only a personal Google Account with Keep Activity on and 18+, at no stated extra cost. Managing saved facts requires a paid Google AI plan. We have not quoted a Google AI plan price because those figures are rendered in the browser and we could not read them from the page itself - check Google's current pricing.
Can Gemini use Tephra?
Gemini CLI can: Tephra's connect page gives a command to add it as a remote MCP server. The Gemini consumer apps are a different matter - Google scopes memory and personalization to its own apps and documents no support for custom MCP connectors there.
Which one can I carry between AI assistants?
Tephra. Google scopes Gemini memory to the Gemini apps, Gemini in Chrome and a smartwatch, with no MCP server and no third-party client, so a developer cannot build on it and a user cannot take it to another assistant. That portability is the whole point of this comparison.
Did you benchmark Tephra against Gemini memory?
No. We have not benchmarked Gemini memory and we make no accuracy claim against it.
More comparisons
Sources
Competitor facts come only from the pages below, accessed 2026-10-10.
- Google Help, personalization with memory of your past Gemini chats: https://support.google.com/gemini/answer/16598469 (accessed 2026-10-10)
- Google Help, get personalization in Gemini Apps: https://support.google.com/gemini/answer/16598623 (accessed 2026-10-10)
- Google Help, manage what Gemini remembers: https://support.google.com/gemini/answer/16598625 (accessed 2026-10-10)