jevcore
litshing/jevcore
JEV core — the judgement primitive and harness for TypeSafe System One (Jev). Closed-set, fail-open, stdlib-only.
Python
- 星标
- 1
- 派生
- 0
收录依据
jevcore 为 System One 提供有界、失败开放的类型化判断原语,并以 harness 将答案标为未验证,等待调用方检查。
litshing/jevcore
JEV core — the judgement primitive and harness for TypeSafe System One (Jev). Closed-set, fail-open, stdlib-only.
jevcore 为 System One 提供有界、失败开放的类型化判断原语,并以 harness 将答案标为未验证,等待调用方检查。
Decide what an AI system should remember: policy-driven memory gating with typed judgments.
共同主题: ai-agents
MCP server exposing TypeSafe's Jev model as a typed evaluate tool.
共同主题: ai-agents
MCP server for Jev (TypeSafe AI's System One model) — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com
共同主题: ai-agents