タグ：langchain

Deep research tool for local knowledge base.

Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.

Fast and cheap agent evals. jev as judge.

Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.

LangChain + Jev (TypeSafe) tutorial: a support-ops agent whose small decisions (triage, model routing, tool guarding, evals) are made by Jev. Real run outputs included.

Use and fine-tune System One models (Jev, Laya) on your data, with an LLM as the teacher.

Static code scanner (SAST linter) that finds insecure usage of Jev / TypeSafe guardrails in Python. Not a guardrail itself — build-time analysis, offline, no API key.