Guided Loop Safety policy plugin for OpenCode

Bigmap for Keyv

Model Context Protocol (MCP) server for Sender.net REST API v2 with human-in-the-loop safety guardrails

MCP server for GeraWitness — Human-in-the-Loop Safety Layer for AI Agents by Gera Services. Placeholder; review-before-commit inbox + cryptographic audit log + GeraSure agent-error insurance, launching 2026.

A safe migration checker for Prisma.

A shim for the setImmediate efficient script yielding API

The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.

Orchestration engine for orc-brain: planner, dispatch loop, safety layer, store.

High-priority task queue for Node.js and browsers

JavaScript Performance Monitor

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Tiny helper to prevent blocking Node.js event loop

High-priority task queue for Node.js and browsers

Algorithmic Agent Harness (ADR-047) — a deterministic control plane that wraps any model/tool/skill as a replaceable worker: utility-scored decisions, four-gate safety, hash-chained receipts, circuit-breaker recovery, adversarial verification, and a bandi

The concrete agent loop plugin for the DeepSeek Harness

Exposes stats about the libuv default loop

Run a list of functions in order in a given object context. The functions can be callback-taking or promise-returning.

fast, tiny `queueMicrotask` shim for modern engines

C function to get the current libuv event loop for N-API

Measure event loop lag