Skip to content
techMEDIUM2026-05-09 05:06 UTC

Compass v0.9 · LongMemEval-S 56.6% · cross-agent memory federation

Compass v0.9 · LongMemEval-S 56.6% · cross-agent memory federation 2026-05-05 · for HN / 知乎 / X / weibo · 1500 字 · 草稿 We achieved 56.6% on LongMemEval-S (n=500) with DeepSeek V3.2 + The killer feature isn't the accuracy. It's cross-agent memory : same user_id across Claude Desktop, Cline, Cursor,

ADVERTISEMENT
⚡ STAY AHEAD

Events like this, convergence-verified across 689 sources, land in your inbox every Sunday. Free.

GET THE SUNDAY BRIEFING →

RELATED · tech