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.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,312 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Ycombinator |
| Canonical URL | https://news.ycombinator.com/item?id=48934870 |
| Publication time | Thu, 16 Jul 2026 14:11:52 +0000 |
| Retrieval time | 2026-07-16T14:34:49.374Z |
| Last seen | 2026-07-16T14:34:49.374Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | vBAUC5ls5U6E |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
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.