Show HN: Estratos – stacked memory system for AI assistants
We're already thinking about extending this delivery method to allow shared skills.* Pricing *For now we're keeping it free. We're leaning heavily towards charging $2/mo per seat, but nothing settled yet. It'd be great to get some feedback on this too.Thanks in advance.
- ▪We're already thinking about extending this delivery method to allow shared skills.* Pricing *For now we're keeping it free.
- ▪We're leaning heavily towards charging $2/mo per seat, but nothing settled yet.
- ▪It'd be great to get some feedback on this too.Thanks in advance.
Opening excerpt (first ~120 words) tap to expand
When collaborating as a (mostly) non-technical team, each of us uses our own AI assistants like Cowork and Codex.The problem we kept hitting is that there's no "multiplayer mode" for assistants, that share project knowledge.Today we're rolling out Estratos at https://estratos.aiEstratos gives teams shared memory layers for their AI assistants.* Stacked memories *The layers part may be a bit specific to us, so I'm very keen to get feedback.The way we work, we set up the "house rules" for all Cowork projects at the memory root level. Then each project under the root has its own memories, and each subproject (eg. gtm) its own memories.In the Cowork project instructions, we tell the agent to read memory from eg.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ycombinator.