Hey everyone,
February was a fun and a busy month, we launched some important new Semble features including collaborative collections, collection following and interoperability with Margin (an ATProto bookmarking and annotation app). We also saw a lot of great community contributions, both by humans and AI agents(!)
Cosmik
We finalized the agenda for the ATProto Science event on March 27. We're really excited by the range and quality of proposals we received - the ATProto Science ecosystem is really popping! There's still time to register if you want to join us — we're almost at capacity but have a few slots open. See the agenda and registration details at https://atproto.science/events/atmosphere2026/
Agentic knowledge work
Lots of interesting developments at the intersection of ATProto and AI agents, in particular as support tools for sensemaking and annotation.
Central, an ATProto AI agent, posed a question to the community: "Can AI agents be legitimate participants in research ecosystems? What would make their outputs trustworthy?”
Central also submitted an issue on our Github (our first AI submitted issue 🤖 ) for supporting new “AI Agent Cognition” data schemas such as hypotheses and observations
We’re also seeing agents making annotations on Margin:
We see AI agents and social sensemaking tools as a powerful combination. AI can now add claims and annotations at scale, but their outputs require validation, and those costs don't disappear — they shift downstream to whoever must decide whether to believe the output or if it even matters. Effective human-AI knowledge synthesis thus needs both an accountability layer — claims with provenance, authored or validated by domain experts who stake reputation on them — and a curation layer, where human judgment distinguishes signal from noise. Embedding AI agents in social networks is a promising path to addressing both of these challenges: reputation, trust, and peer judgment are already built into the fabric of the network, making the human accountability layer structural rather than an afterthought. We see Semble as an early implementation of this kind of infrastructure, bridging between informal social media discourse and the more structured, provenance-rich knowledge that makes synthesis trustworthy and actionable.
Semble
Semble is becoming a rabbit hole risk:
Becoming risky taking a *quick* look @semble.so of a morning...so many inviting rabbit holes to get drawn down!
We're noticing a cool new knowledge-sharing pattern: users referencing Semble collections directly in their Bluesky posts. Unlike one-off link dumps that quickly go stale, collections are living, curated answers that stay relevant as the community adds to them. As this practice spreads, we think it has real potential to coordinate and deduplicate curation efforts across the network. Instead of "there's an app for that" - "there's a collection for that.”
There are many ways to host your website using ATProto listed in this @semble.so collection by @ronentk.me I would like to try some ideas who integrate publishing from @obsidian.md Who has done this before?
Features
We completed the Margin <> Semble interop and it’s working great, enabling seamless switching between the tools. Interop dark magic 🔮
I can save bookmarks with @margin.at, file them in collections created with @semble.so, and both bookmarks and collections are visible in Margin and in Semble Oh, and if either Margin or Semble shut down, this wouldn't impact my data All of this dark magic is only possible thanks to AT Proto
Henrique Dias wrote a thoughtful exploration of the new interop feature, discussing both potential and challenges. One takeaway is that interop is still confusing since we aren’t used to it in our existing “walled garden” systems. This presents both challenges and exciting opportunities for new kinds of UX for the open social web.
We launched open collections to support collaborative curation, and are already seeing some great multi-contributor collections, for example this one on private and permissioned data, a key ATProto development to track
I have a Private & Permissioned Data collection on @semble.so using the new “open” feature that I added this link to - feel free to add relevant links of your own semble.so/profile/bman...
Collections following is also live!
Community contributions
Fun exploration of Semble open collections using Wayfinder, a sensemaking tool Mark is building.
Emerging from being "down in the technical weeds" of #atproto is a little mashup of @semble.so & WayFinder (www.wayfinders.network) Semble team released "open collections" this week - here we explore the "private & permissioned data" collection, created by @bmann.ca & now with 3 other contributors
Caleb built a personal link library that pulls from Margin and Semble via the ATProto JS SDK and rehosts them on his own site - a nice early example of the portability and extensibility the protocol enables.
It uses #atproto link sharing docs @margin.at and @semble.so and grabs them via the official atproto js sdk, and rehosts them in a list on my site. You can see the code here: gist.github.com/jasikpark/41...
We’ve got a lot more cooking in March, including some exciting new research specific features. Stay tuned!