AI memory comparison
Tephra vs Zep
Zep describes itself as a context layer for enterprise data built on temporal context graphs, with an open-source framework called Graphiti. Tephra is a hosted memory for individuals and teams connecting AI apps. Zep fits enterprise and agent-builder needs; Tephra fits people who want their AI apps to share one memory.
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 Zep side by side
| Feature | Tephra | Zep |
|---|---|---|
| What it is | A hosted memory your connected AI apps share: they recall from it and write to it over MCP or REST. | A context layer for enterprise data that organizes business data, documents and conversations in temporal context graphs. Graphiti is its open-source graph framework. [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. | Free plan with 10,000 credits a month. Flex is $125 a month, Flex Plus is $375 a month, Enterprise is custom. [2] |
| How usage is limited | No usage metering. There are only abuse limits: 60 requests a minute per key and 120 a minute per member. | Monthly credits spent on the data you send (each Episode); overage is billed per credit block. The page also lists per-minute rate limits and project limits by plan. [2] |
| 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 free plan lists 1 Memory MCP Server seat and paid plans list more (5 on Flex, 15 on Flex Plus). Separately, the documentation offers a Claude Code and Codex plugin that bundles a skill with the Zep docs MCP server - that one is documentation, not memory. [2] [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. | The overview describes governance features (access control, data-source tracing, activity review) and the Enterprise plan lists audit logs. Per-user memory editing is not described on the pages we read. [2] [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 service, with Enterprise options for cloud with your own encryption keys or deployment in your VPC. Graphiti is open source. Enterprise lists SOC 2 Type II and HIPAA BAA. [2] [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. | Consolidates business data, documents and conversations into the context graph. [1] |
Where Zep is better
- Zep. It targets enterprise requirements: temporal context graphs, governance, and SOC 2 Type II and HIPAA BAA on the Enterprise plan. Tephra makes no such claims. Zep organizes data in temporal context graphs, and Graphiti builds temporal knowledge graphs, while Tephra's stale-fact handling is partial. [1] [2]
Choose Zep if: You need temporal context graphs, governance, audit logs or SOC 2 Type II and HIPAA BAA on an Enterprise agreement, or you want open-source Graphiti.
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 personal or small-team memory that connected AI apps share, at a flat price with no credit overages.
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 much does Zep cost?
Zep lists a free plan with 10,000 credits a month, Flex at $125 a month with 50,000 credits and Flex Plus at $375 a month with 200,000 credits, as read on 2026-10-10.
Is Zep open source?
Graphiti, Zep's temporal knowledge graph framework, is described as open source. The Zep service itself is sold as a cloud product.
Did you benchmark Tephra against Zep?
No. Zep was not run in our test. Zep organizes data in temporal context graphs, while Tephra's stale-fact handling is partial.
More comparisons
Sources
Competitor facts come only from the pages below, accessed 2026-10-10.
- Zep documentation overview: https://help.getzep.com/overview (accessed 2026-10-10)
- Zep pricing: https://www.getzep.com/pricing (accessed 2026-10-10)