29 results
Guardian-style auto approval for DeepSeek Harness, aligned with Codex's Approve for me: a judge model reads the session transcript, verifies local state with read-only tools, and scores risk x authorization against a declarative policy before granting (out-of-tree plugin)
DataTally: verifiable public usage profiles of data assets for DeepSeek Harness. search_assets / get_asset_profile / compare_assets. DataTally records; you judge.
AI-reviewed auto-approval for DeepSeek Harness: judges each pending approval ask with one auxiliary model call before any human answerer runs, auto-grants the safe ones, and escalates everything else with the review analysis attached
DSH memory plugin gated by the TypeSafe Jev decision model: mem_* tools whose every read/write is a typed judgement (choice/noul) — write gate, recall gate and a fail-closed injection gate with budget, audit log and restore/merge.
Ask Jev (TypeSafe System One) typed questions from DeepSeek Harness: batch judgements with probabilities, configured per user in Settings.