langchain-loadout 0.1.1

Per-turn skill selection for LangChain and deepagents agents: the model sees the few skills it needs, not a catalog of hundreds.

Quick start · Results · Documentation · Contributing

Why Loadout

Large skill catalogs take up context on every model call. Loadout ranks and verifies skills for each user turn, then loads the relevant instructions or suggests candidates. The agent can also search the catalog with find_skill.

Quick start

1. Install. Requires Python 3.11+. The jev extra includes the judge adapter and its SDK.

pip install "langchain-loadout[jev]"

2. Connect your skills. Place them in ./skills/<name>/SKILL.md with name and description in YAML front matter. Set TYPESAFE_API_KEY and your model provider's credentials (ANTHROPIC_API_KEY for this example).

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

from langchain_loadout.langchain import LoadoutSkillsMiddleware
from langchain_loadout.providers.jev import JevJudge

backend = FilesystemBackend(root_dir=".", virtual_mode=True)
loadout = LoadoutSkillsMiddleware(backend=backend, sources=["/skills/"], judge=JevJudge())

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-5",
    backend=backend,
    skills=["/skills/"],
    middleware=[loadout],
)
await agent.ainvoke({"messages": [{"role": "user", "content": "I need a statement for the embassy"}]})

Run the example in an async context. Selection runs on ainvoke and astream; synchronous calls use the ordinary skills middleware. Tune thresholds and questions through Settings.

The public API is evolving: minor releases may introduce breaking changes while the version is 0.x.

Results

Measured on a bank-statement assistant using deepagents: 236 skills, 250 turns.

These results use generated data, one judge and one agent model. Selection added roughly 3 seconds on this catalog; total cost per turn was slightly higher because changing prompts reduced cache reuse. Fit thresholds to your own data. Measurement context and limits →

Documentation

License

MIT © 2026 Ivan Deyna