AI memory comparison
Tephra vs Basic Memory
Basic Memory keeps your memory as plain Markdown files you own, reachable by AI assistants over a hosted MCP server with OAuth, and it is free and open source to run locally. It is the closest competitor to Tephra in shape and, on transparency and portability, it is ahead of us. Tephra's case is the shared library and a flat price; read the section on where Basic Memory is better before choosing.
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 Basic Memory side by side
| Feature | Tephra | Basic 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 knowledge base you own: a knowledge graph written in plain Markdown files, reachable by AI assistants over MCP. Its pitch against built-in memory is that yours is "large, structured, and inspectable" and the files stay yours. [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. | Free and open source to run on your own machine. Cloud Team is $15 per seat a month ($13 at 10+ seats, $12 at 20+), Business is $30 per seat a month. Every cloud plan starts with a 7-day trial. Read 2026-10-10. [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. | Per active seat on cloud, with volume breaks; notes and version history are "unlimited" subject to fair use. Only its agent-infrastructure tier is credit-metered. Running it locally is unmetered. [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. | The widest reach of any competitor here. Hosted MCP at cloud.basicmemory.com/mcp with OAuth and no local install, published in the Claude Directory so it installs across Claude web, desktop, mobile, Claude Cowork and Claude Code, plus a ChatGPT app. API keys are available as an alternative. [2] |
| 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. | The strongest in this table. Memory is Markdown you can open in any editor or in Obsidian; cloud adds a note editor, per-note file history with restore, point-in-time snapshots with rollback, comments and suggested edits, and documented deletion semantics for both local and cloud copies. [2] [3] |
| 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. | AGPL-3.0 and local-first by default, with cloud opt-in per project and a documented mix of the two. Note that AGPL can itself be a blocker for some commercial reuse, though the hosted cloud sidesteps that for an ordinary user. [4] [3] |
| 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. | Explicit tool calls from the assistant, writing the Markdown yourself in any editor, and importing project archives or Claude and ChatGPT exports. Automatic capture appears only as a "Harness Capture" entry in the cloud docs navigation, with no description in the body text we read. We found no Gmail, Slack or Drive connectors. [2] |
Where Basic Memory is better
- Basic Memory. Matches Tephra's hosted-MCP-plus-OAuth story and then adds distribution Tephra has not got: a Claude Directory listing that installs across Claude web, desktop, mobile, Claude Cowork and Claude Code, plus a ChatGPT app. Its transparency beats ours on the merits rather than the marketing, because memory is Markdown on disk with per-note version history, snapshot rollback and suggested edits. It is free forever locally under AGPL-3.0, so there is no cost to try and a clear answer to "what if the vendor disappears", and exit is a file copy rather than a migration. Its cheapest paid tier, $15 a seat, undercuts ours, and it offers SSO/SAML and HIPAA-compliant hosting at $30. [2] [3] [4] [1]
Choose Basic Memory if: You want to own the files outright, audit and correct what is stored, and be able to leave with a folder copy. You also get a free local option, a $15 seat that undercuts us, per-note version history with restore, and SSO/SAML with HIPAA-compliant hosting at $30 a seat.
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 want a shared library of public research added to hourly alongside your own memories, a flat price with no per-seat maths, and no files or local install to manage. On reach the two are close: both offer hosted MCP with OAuth, and Basic Memory additionally has a Claude Directory listing and a ChatGPT app.
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 Basic Memory free?
It is free and open source under AGPL-3.0 to run on your own machine. Its cloud is $15 per seat a month for Team ($13 at 10+ seats, $12 at 20+) and $30 per seat for Business, with a 7-day trial on every cloud plan, as read on 2026-10-10. Tephra has no free tier.
Which one lets me see and correct what is stored?
Basic Memory, and we would rather say so than pretend otherwise. Its memory is Markdown you can open in any editor, and its cloud adds per-note file history with restore, point-in-time snapshots with rollback, and comments and suggested edits. Tephra lets you edit, delete and pin a memory and keeps edit history, but it is a view of a hosted store, not files you hold.
What does Tephra have that Basic Memory does not?
A shared library of public research and regulatory material - arXiv, PubMed, the Federal Register, SEC 8-K filings, Wikipedia and others - that is added to every hour and that recall draws on beside your own memories. We found no equivalent in Basic Memory.
Did you benchmark Tephra against Basic Memory?
No. We have not benchmarked Basic Memory and we make no accuracy claim against it.
More comparisons
Sources
Competitor facts come only from the pages below, accessed 2026-10-10.
- Basic Memory home page: https://basicmemory.com (accessed 2026-10-10)
- Basic Memory documentation, cloud guide: https://docs.basicmemory.com/cloud/cloud-guide (accessed 2026-10-10)
- Basic Memory pricing: https://basicmemory.com/pricing (accessed 2026-10-10)
- Basic Memory source repository (AGPL-3.0): https://github.com/basicmachines-co/basic-memory (accessed 2026-10-10)