AI memory comparison
Tephra vs ChatGPT memory
ChatGPT memory is built into ChatGPT, needs no setup and has clear on and off controls. It is a feature of one app. Tephra is a separate hosted memory that ChatGPT and other MCP apps can connect to, which matters if you switch between AI tools. If you only use ChatGPT, its own memory may be all you need.
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 ChatGPT memory side by side
| Feature | Tephra | ChatGPT 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 feature inside ChatGPT that can draw on past chats, saved memories, custom instructions, files in Library and, depending on plan and region, content from connected apps such as Gmail. [1] |
| 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. | The help page says memory features and controls vary by plan, region, platform and workspace settings. It gives no memory price. [1] |
| How usage is limited | No usage metering. There are only abuse limits: 60 requests a minute per key and 120 a minute per member. | The help page says there is no separate storage limit for what ChatGPT can reference through chat history. [1] |
| 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. | The controls described are inside ChatGPT. The help page does not describe sharing that memory with other AI apps. [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. | Settings, Personalization, Memory: a memory summary you can correct, saved memories you can edit or delete, and sources shown under responses. Temporary chats do not create or update memories. OpenAI may retain logs of deleted saved memories for up to 30 days. [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. | A vendor-hosted feature of ChatGPT. [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. | From past chats, saved memories (details you ask it to remember or that it saves), custom instructions, Library files and, depending on plan and region, connected apps. [1] |
Where ChatGPT memory is better
- ChatGPT memory. It needs no setup if you already use ChatGPT, the controls live in the app you are already in, and it can draw on files and, depending on plan and region, connected apps such as Gmail. Tephra has no member connectors. [1]
Choose ChatGPT memory if: You use ChatGPT almost exclusively and want memory with no setup. ChatGPT memory is also genuinely ahead of Tephra in three ways its help page describes: it builds memory from your past chats automatically, where Tephra only saves when your AI calls tephra_remember; it can draw on connected apps such as Gmail and on files in Library, which Tephra has no connectors for; and it is included in a plan you may already pay for, where Tephra has no free tier.
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 move between several AI apps or accounts and want one memory that all of them read and write.
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
How do I turn off or delete ChatGPT memory?
OpenAI's help page says to use Settings, Personalization, Memory to review and change controls, and that you can delete saved memories there or ask ChatGPT to forget them. Deleting a chat alone does not necessarily delete a separate saved memory.
Can ChatGPT use Tephra?
Tephra's connect page lists ChatGPT among MCP apps that can sign in with OAuth. Tephra's OAuth discovery endpoints were verified live on 2026-10-10; test the sign-in in your own app before relying on it.
Is Tephra a replacement for ChatGPT memory?
Not necessarily. They can be used together; ChatGPT memory covers what happens inside ChatGPT, and Tephra covers memory you want shared with other connected AI apps.
More comparisons
Sources
Competitor facts come only from the pages below, accessed 2026-10-10.
- OpenAI Help Center, Memory in ChatGPT: https://help.openai.com/en/articles/8590148-memory-in-chatgpt (accessed 2026-10-10)