OpenAI reinvents Recall except everything is stored remotely
pluc
12 points
5 comments
April 22, 2026
Related Discussions
Found 5 related stories in 111.6ms across 10,324 title embeddings via pgvector HNSW
- Show HN: AI memory with biological decay (52% recall) SachitRafa · 82 pts · April 26, 2026 · 60% similar
- Show HN: MCPs aren't enough, give Codex/Claude accurate memory of everything midas · 16 pts · May 26, 2026 · 57% similar
- Recall – local multimodal semantic search for your files patel_aayushya · 17 pts · April 06, 2026 · 55% similar
- Show HN: YourMemory, agentic memory is a pruning problem, not a hoarding problem SachitRafa · 19 pts · June 07, 2026 · 55% similar
- I built a better, human like memory, for Agents emson · 11 pts · March 29, 2026 · 53% similar
Discussion Highlights (4 comments)
danpalmer
Microsoft's biggest PR blunder in years. OpenAI: Hold my beer
lemonish97
Isn't this exactly why Microsoft had to recall 'Recall'?
LiamPowell
Title does not match the title on the page, or even the content on the page for that matter: > Screen captures are ephemeral and will only be saved temporarily on your computer.
spijdar
This isn't the sort of thing I'm personally interested in -- I've been playing with incorporating LLMs into my work lately, but with the caveat that the harness software has to be relatively simple and the models have to be local -- but I don't think this is really like Recall at all. The problem with Recall was that it was opt-out and deployed everywhere (that supported it, as I understand). This, assuming it stays opt-in, makes much more sense. When I play with Google's Antigravity, I run it in a VM. There, where my environment literally only contains something I'm working on, a feature like Recall could be genuinely useful.