JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: fix the stale benchmark table and finish the one-liner sweep

Browse Source 
Addresses review feedback on #6944.

The Performance Improvements table in platform-v2-to-v3.mdx still read
91.6 (+20.2) / 93.4 (+25.6) while the Overview prose in the same file
already read 92.5 / 94.4, so the page stated both sets of numbers.
Reconciled against the research team's current figures in README.md:
71.4 -> 92.5 (+21.1) and 67.8 -> 94.4 (+26.6).

Delivered the three one-liner sweep edits the PR description claimed but
never shipped: the README banner alt text, the mem0-ts README title and
lede, and the docs/introduction.mdx frontmatter description.

The dated changelog entry at 91.6 / 93.4 stays as-is; it records what was
announced on 2026-04-14.
This commit is contained in:
kartik-mem0
2026-08-14 18:38:06 +05:30
parent bc5a7d763d
commit 08a5a931e0
4 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/introduction.mdx
+1 -1
View File
@@ -1,6 +1,6 @@
---
title: "Build AI apps that remember"
description: "Add persistent, self-improving memory to your AI app with Mem0 Platform or self-hosted Open Source."
description: "Give your AI agents persistent memory with Mem0 Platform or self-hosted Open Source."
mode: "custom"
---
docs/migration/platform-v2-to-v3.mdx
+2 -2
View File
@@ -293,8 +293,8 @@ If your application previously read graph relations from the API response (`rela
| Metric | Previous Algorithm | New Algorithm |
|---|---|---|
| **LoCoMo Overall** | 71.4 | **91.6** (+20.2) |
| **LongMemEval Overall** | 67.8 | **93.4** (+25.6) |
| **LoCoMo Overall** | 71.4 | **92.5** (+21.1) |
| **LongMemEval Overall** | 67.8 | **94.4** (+26.6) |
| **Extraction latency (p50)** | ~2.0s | **~1.0s** |
| **Mean tokens per query** | N/A | 6.8-7.0K (top200) |