344 projects · updated 2 November 2026
Built with decision models
What people are actually putting these models inside, five days after the category existed. Sorted by the job, not by star count.
The shape of this list says more than any individual entry does.
Developer tooling dominates, because a coding agent makes hundreds of cheap decisions per session and each one used to cost a full model call. Browser extensions come next, where a decision that takes a second is a decision nobody waits for. Almost nothing here is a chatbot.
277 of the 344 call the hosted API rather than running open weights. That is worth knowing if you are choosing between the two: the ecosystem is currently built on a single vendor, and the open-weight side is younger than the interface. If you would rather not depend on that, start at self-hosting.
Where the decision runs
By what it does
Developer tooling 84
Code review gates, CI checks, agent harnesses and editor plugins. The densest cluster in the ecosystem, because a coding agent makes hundreds of small decisions per session and each one costs something.
Open reimplementations 80
People rebuilding the category from open weights: one-pass scorers, constrained decoding over local models, and small models trained to return a calibrated distribution. The fastest-moving cluster here.
Agents 30
Tool selection, routing and step gating. An agent choosing its next action is the purest version of the problem this class of model exists for.
Language integrations 30
Libraries that make a typed decision feel native to a language: pattern matching on an answer in Elixir, a probabilistic if in Ruby, a typed method via BAML.
Browser 22
Extensions and automation that judge pages: what to hide, what to click, what is worth reading. Latency matters here in a way it does not on a server.
Evals and benchmarks 18
Head-to-head races, task suites and benchmark harnesses. Read the method before the headline: most of these compare on speed and cost, and very few report calibration.
Content 17
Moderation, summarisation triage, voice and video. Judging content rather than producing it.
Robotics and games 17
Embodied agents and game-playing systems, where a decision happens every tick and a generated reasoning trace per step is not affordable.
Search and retrieval 15
Source selection, query routing and relevance filtering. Deciding which retrieved chunks are actually worth passing on is a classic typed decision.
Trading 14
The highest-stakes cluster here, and the one where calibration matters most. A confidence number you cannot trust is worse than no confidence number.
Everything else 11
Projects that do not fit the larger clusters, including data tooling, recruiting and one-off experiments.
Databases 6
Extensions that put a typed decision next to the data: classify a Postgres row in SQL, or navigate a graph one choice at a time.
Most starred
Star counts read on 2026-11-02. They measure attention, not whether the project works.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.