Tandem is the authority layer for AI-first work: runtime authority for agents, tools, memory, approvals, and audit trails.

Control plane and operator workbench for governed agent tool execution with policy, approvals, audit and evidence on Kubernetes. Includes a full UI for Linux, macOS and Windows.

GAP (Governed Agentic Programming) main repository | The native instruction language of AEP (Agent Element Protocol) | Fully deterministically programmed AI agents. | Paid version GAP runtime will be available on the NLA website soon.

Governed runtime orchestration and continuity infrastructure for consequence-bearing autonomous systems.

Deterministic execution-governance infrastructure for consequence-bearing autonomous systems.

Agent gateway for external tools — Rhumb Index scores services; Rhumb Resolve routes supported capability calls through governed execution rails.

Elixir SDK for the Google Antigravity CLI (agy) — stream-json headless sessions, governed launch, and stack integration via cli_subprocess_core and agent_session_manager. Standalone execute/run APIs, materialized governed credentials, multi-instance isolation, and Hex-ready docs for nshkrdotcom AI SDK consumers.

Elixir SDK for the Cursor Agent CLI (agent) — stream-json headless sessions, governed launch, and stack integration via cli_subprocess_core and agent_session_manager. Standalone execute/run APIs, external auth via CURSOR_API_KEY, multi-instance subprocess isolation, and Hex-ready docs for nshkrdotcom AI SDK consumers.

Independent reference implementation of governed agentic AI execution (policy gates, deterministic tools, provider-neutral adapters)

Approve, refuse, or defer AI actions before they run.

Approve, refuse, or defer AI actions with proof.

Provide a Python toolkit for research with live benchmarks and tested modules to support code development and evaluation.