Workspace context loader for AGENTS.md/CLAUDE.md instruction files

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.

JSON becomes real things. Define your catalog, register your components, let AI generate.

Cedar policy enforcement and signed receipts for AI agent tool calls, guided repository review, bounded coding work and exact human approvals. Built by ScopeBlind.

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)

Client command surface: global directory cache, '/' source, three command UI kinds, popupSelect registry

Repeat-tool-call guard plugin: advisory reminders when an agent loops on identical tool calls

Opt-in durable per-step context with the current time and elapsed time

Model-facing skill loading tool for the DeepSeek Harness

Shared Claude Code / Codex hook wire protocol: matcher engine, stdin/exit-code/stdout codec, multi-hook merge, and hook/* session events

DPoP (RFC9449) for JavaScript Runtimes

Abstract user-questions seam (ctx.userQuestions) for asking the human during agent runs

Web ask_user_question feature: host tool mount plus composer-takeover question UI

Locale plugin: Host-backed zh/en preference, browser-derived fallback, locale snapshots, and typed namespace dictionaries

iden3-auth implementation in JavaScript

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

Sandbox-consuming implementation of the DeepSeek Harness PowerShell executor seam (confines every command via ctx.sandbox, reports denial/enforcement result facts)

One-call governance for any MCP server. Wraps every tool.call() with policy evaluation, signed execution receipts, and an optional approval gate — no changes to your tool implementations required.

Portable AgentsKit runtime for chat orchestration, tools, memory, and retrieval.

Agent evaluation and benchmarking for AgentsKit.