Your agent runs the project through a verified loop: task → artifact (ADR / spec / epic / story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in git — any model can pick the project up tomorrow.

Multi-provider coding-agent orchestration: run Claude Code, Codex, Gemini and more in one verified loop where a critic on a different model signs off before work ships

Verified Loop multi-agent system for rigorous research and development in opencode and Claude Code

A shim for the setImmediate efficient script yielding API

A verifiable self-improvement loop for agent harnesses. Freeze the model. Evolve the harness. Promote only what proves lift.

High-priority task queue for Node.js and browsers

JavaScript Performance Monitor

Standalone agent runtime with ReAct loop for AgentsKit.

High-priority task queue for Node.js and browsers

Passport authentication strategy using JSON Web Tokens

Tiny helper to prevent blocking Node.js event loop

The concrete agent loop plugin for the DeepSeek Harness

fast, tiny `queueMicrotask` shim for modern engines

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.

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

Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold

Locutus other languages' standard libraries to JavaScript for fun and educational purposes

Measure event loop lag

Polyfill for perf_hooks.monitorEventLoopDelay(...)