langchain-loadout
Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.
How it uses Jev
A drop-in replacement for the deepagents SkillsMiddleware : on each user turn a fast judge decides which SKILL.md skills are needed, and only those are loaded, so a catalog of hundreds stays out of the prompt. Bring any judge: a hosted model, a self-hosted one, or plain rules. An adapter for Jev is included.
Getting started
Put skills in ./skills/ /SKILL.md , with name and description in YAML front matter (the Agent Skills format deepagents uses). Set TYPESAFE API KEY (get a key) and your model provider's key. Jev is the judge in this example; see below for your own.
- Languages
- Python 99% · Just 1%
- License
- MIT
- Latest release
- v0.3.0
- Last activity
- Sep 2026
- Added
- 2026-09-23
- Stars at snapshot
- 3
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.
