179,387 packages matching “ai-decision-audit”
@deepseek-ai/dsh-user-approval
v0.0.1-rc.1 · 1 month ago
User-approval seam (ctx.approval) for the DeepSeek Harness: one-shot permission decisions dispatched to composed answerers over the approval/request waterfall, fail-closed by default
No known vulnerabilities
@json-render/core
v0.21.0 · 7 days ago
JSON becomes real things. Define your catalog, register your components, let AI generate.
No known vulnerabilities
@cohesionauth/sdk
v1.5.0 · 2 months ago
Official TypeScript SDK for the COHESION Judgment Independence Score API. Real-time oversight scoring for AI-assisted human decisions, per EU AI Act Article 14, Colorado SB 205, and NYC Local Law 144.
No known vulnerabilities
@deepseek-ai/dsh-fs-observation-policy
v0.0.1-rc.3 · 1 month ago
File-context policy plugin for the DeepSeek Harness — observed-state, read-before-edit, and version-guarded write/edit added over the ctx.fs provider seam through the fs/* event gate (no service API)
No known vulnerabilities
governance-sdk
v0.20.0 · 1 month ago
AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents
No known vulnerabilities
@strixgov/verifier
v1.24.1 · 15 days ago
Independent verification of Strix governance evidence, approval artifacts, linked attestations, tool-gateway authorization receipts, signed execution outcomes, chain snapshots, and connected-mode wire envelopes. Offline-capable. No Strix account required.
No known vulnerabilities
@deepseek-ai/dsh-client-ui-commands
v0.0.1-rc.3 · 1 month ago
Client command surface: global directory cache, '/' source, three command UI kinds, popupSelect registry
No known vulnerabilities
@deepseek-ai/dsh-repeat-tool-reminder
v0.0.1-rc.3 · 1 month ago
Repeat-tool-call guard plugin: advisory reminders when an agent loops on identical tool calls
No known vulnerabilities
@deepseek-ai/dsh-time-context
v0.0.1-rc.1 · 1 month ago
Opt-in durable per-step context with the current time and elapsed time
No known vulnerabilities
@deepseek-ai/dsh-tool-skill
v0.0.1-rc.1 · 1 month ago
Model-facing skill loading tool for the DeepSeek Harness
No known vulnerabilities
@deepseek-ai/dsh-hook-protocol
v0.0.1-rc.1 · 1 month ago
Shared Claude Code / Codex hook wire protocol: matcher engine, stdin/exit-code/stdout codec, multi-hook merge, and hook/* session events
No known vulnerabilities
audit-ci
v7.1.0 · 2 years ago
Audits NPM, Yarn, and PNPM projects in CI environments
No known vulnerabilities
@deepseek-ai/dsh-agent-instructions
v0.1.0-rc.6 · 1 month ago
Workspace context loader for AGENTS.md/CLAUDE.md instruction files
No known vulnerabilities
@deepseek-ai/dsh-user-questions
v0.0.1-rc.3 · 1 month ago
Abstract user-questions seam (ctx.userQuestions) for asking the human during agent runs
No known vulnerabilities
@deepseek-ai/dsh-session-format-v2-to-v3
v0.1.5-alpha.1 · 17 days ago
Streaming system-prompt, canonical-envelope and PTC migration into V3
No known vulnerabilities
@deepseek-ai/dsh-client-ui-user-questions
v0.0.1-rc.3 · 1 month ago
Web ask_user_question feature: host tool mount plus composer-takeover question UI
No known vulnerabilities
ax
v0.8.1 · 8 days ago
Score any site's agent readiness and watch real AI agents navigate it — powered by ora
No known vulnerabilities
verdaccio-audit
v13.1.4 · 5 days ago
Verdaccio Middleware plugin to bypass npmjs audit
No known vulnerabilities
@deepseek-ai/dsh-client-locale
v0.0.1-rc.1 · 1 month ago
Locale plugin: Host-backed zh/en preference, browser-derived fallback, locale snapshots, and typed namespace dictionaries
No known vulnerabilities
@deepseek-ai/dsh-pwsh-sandbox
v0.0.1-rc.1 · 1 month ago
Sandbox-consuming implementation of the DeepSeek Harness PowerShell executor seam (confines every command via ctx.sandbox, reports denial/enforcement result facts)
No known vulnerabilities