loop through commands in fun and amazing ways!

one rAF to rule them all

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

Loop engineering for software development. Turn any repo into a self-organizing AI team — 8 specialists, evidence-gated phases, parallel feature voyages.

Middy AWS Lambda event loop tracer middleware

Size Limit preset for big open source libraries

Model-facing fresh-agent Ralph loop over the workflow and subagent seams

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

Immune-Brain agent skill system

A webpack loader to transform ∞ loops so that they throw

Prevent infinite loops and recursion in dynamically eval'd JavaScript.

An async stream which can be iterated over using a for-await-of loop.

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

Node-RED nodes to looping (fixed steps, condition based or iterating over arrays, objects, maps, sets, string).

The most efficient JS implementation calculating the Levenshtein distance, i.e. the difference between two strings.

the fastest version of Function#bind I could make

worker-thread workflow engine: executes model-written orchestration scripts off the host event loop, bridging agent() calls back to ctx.subagents

Semantic loop-engineering for agent-owned, visible, interruptible continuation in Pi

Big-friendly JSON. Asynchronous streaming functions for large JSON data sets.

Mechanical enforcement of LOOP.md/docs/safety.md's path denylist and auto-merge allowlist — evaluate a proposed change against static policy and block or allow it.