Articles
What we have learned building shared memory for coding agents: the questions teams ask before adopting it, what it changed for one team, how we measure it, and why we build it.
-
ArticleOctober 2026
Why does your engineering team need a memory product?
AI coding agents made every engineer faster, and scattered what the team knows across sessions that forget. The questions to ask before adopting a memory product, and our answers.
Read the article → -
Customer storyOctober 2026
How SimpleRose stopped running the same experiment twice
SimpleRose builds optimization solvers. Its coding agents now share a memory of what the team has already tried, so lessons from one developer’s experiments reach the next session.
Read the story → -
Benchmark reportOctober 2026
Assertion Memory scores 81.1% on BEAM 100K, ahead of the leading memory system.
What the public BEAM benchmark tests, how we measured, how the result compares with other memory systems, and where memory still has gaps.
Read the report → -
Our thesisSeptember 2026
AI that builds on its own reasoning.
Today’s agents start every session from zero. Why we think the next stage is AI that remembers what was decided and why, tests new claims against evidence, and builds on what survived.
Read the thesis →
Give your team’s coding agents a shared memory.
Works with Claude Code, Codex and Cursor. Free to start.