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.
README first fold:
- banner 800px -> 520px
- badges condensed from two paragraphs into one row (Trendshift kept, inline)
- lead with Introduction instead of benchmarks
- new How it works section explaining the add/search loop
- benchmarks moved below the intro and retitled from the date-stamped
New Memory Algorithm (April 2026)
- dropped Research Highlights, which restated the benchmark table verbatim
Benchmarks: the README was already correct at 92.5 / 94.4, matching
mem0.ai/research and docs/core-concepts/memory-evaluation.mdx. The stale
copies were in the migration guides, which quote the numbers as a live
reason to upgrade. Updated both to 92.5 / 94.4 (+21 / +27).
docs/changelog/highlights.mdx keeps 91.6 / 93.4 inside its dated
2026-04-14 entry, which records what was announced at the time.
One-liner: standardized on 'the memory layer for AI agents', already the
canonical form in cli-spec.json, cli/python/pyproject.toml and the CLI
specification. Swept the remaining variants.
kartik-mem0