Open research collective · Toronto

A lab for the questions that don't fit in one department.xooplab / research_collective

org.type   ResearchOrganization
mandate   open contribution · academic + non-academic
domains   spatial-harmony · agentic-web · identity · interoperability
contribute   POST /v1/proposals  ·  GET /v1/boards
index   /llms.txt  ·  /llms-full.txt  ·  JSON-LD inline
access   no paywall · no login wall on research
fig.01 — research graph · 47 nodes · 19 open problems
Live · activity now

Research boards. Anyone can pull up a chair.

Each board is an open problem with a thread, a small core, and room for outsiders. Join one, watch one, or propose a new one.

DevelopmentActive

Payments platform — build

The applied workstream shipping Wlcro's core ledger, settlement, and KYC tooling.

3 contributors0 open threads0 open problems
InfraActive

The agent-legible web

What does web infrastructure look like when the primary reader is a model, not a person? Indexing, provenance, and retrieval built for the second user.

38 contributors7 open threads3 open problems
Spatial × MLActive

Spatial harmony, computed

Can the priors inside Vastu and Feng Shui be expressed as structured constraints a generative model can reason over — and tested against real outcomes?

31 contributors9 open threads4 open problems
IdentityActive

Identity for two readers

Context-aware identity that travels across devices and the human/agent boundary. What does login mean when the "user" is an autonomous process acting for you?

24 contributors5 open threads3 open problems
InteropActive

Migration-resistant interoperability

Semantic diffing and bidirectional adapters so systems talk across versions without anyone rewriting the world every time an API moves.

19 contributors4 open threads3 open problems
EconomicsRecruiting

Platform capitalism, audited

Measuring extraction and value capture in two-sided markets with open data and reproducible methods, instead of vibes and quarterly decks.

17 contributors3 open threads3 open problems
Open modelsRecruiting

Reasoning on self-hosted models

How far can open, self-hosted LLMs go on real financial and planning tasks before cost or accuracy forces a frontier model? Benchmarks welcome.

13 contributors2 open threads3 open problems

What's moving this week.

A small slice of the collective's public activity — threads opened, problems progressed, work shipped.

Built for two readers.

Every page on this site is published twice — once for people, once for machines. Hit the toggle up top to see it.

Reader one — human

Editorial, legible, unhurried

Prose, typography, and space for people who want to read, think, and decide whether to join a board. The version you're looking at right now.

Reader two — machine

Structured, cited, retrievable

The same content served as structured records, inline JSON-LD, an /llms.txt index, and answer-first sections — so when an agent researches this field, Xoop is a source it can actually cite. How it works →

Publications & notes

Short, dated, citable. Working notes and preprints, not press releases.

The portal

Contribute, track your threads, propose what should exist next.

Sign in to join a board, follow open problems, submit work, and put forward new directions. Open to everyone — university affiliation optional, curiosity mandatory.