The PathMan pages › awembed

awembed(tool, public)

Train an embedding model that knows your corpus, and prove it beats the big one.

Name

awembed — Train an embedding model that knows your corpus, and prove it beats the big one.

The problem it solves

Every agent stack searches your code with an embedding model trained on someone else's. It is right about two thirds of the time on a corpus it never saw, and nothing in the stack measures that. Distilling a small student on your own corpus -- the big model's margins plus your labels -- beats the big model, and the eval that proves it is the part people skip.

Instead of trusting / you check

instead of trusting
a general-purpose embedder that has never seen your code
you check
a held-out split of whole directories, scored teacher vs student vs int8

Adopt it alone

Point it at one repo and get a 0.6B embedder that ranks your directories better than the 7B one it learned from, with the eval that proves it.

Install

install
pip install awembed

Where it sits in the path

  • Not on the path yet — reference only.

See also

awdk · awgraph · awm · awfind · awrecurse · awrepl · awsh · awskills

Generated 2026-09-14 00:48Z from the ecosystem registry. A field here that is wrong is wrong in the registry — fix it there and this page follows.

One estate, 8 doors

These projects are organs of the same system — the same identity plane, the same agent runtime, the same operational discipline. Follow any of them.

The ecosystem this belongs to

Every Aitherium repository publishes an aither-manifest.json beside its page, and each surface reads all of them — so the network is browsable from any node in it.