Tools

Brainstorming, TDD, and subagent-driven development loops.

Official plugin; a stop-hook re-feeds your prompt until the task is done.

Canonical autonomous loop; fresh context each iteration to avoid context rot.

Ralph loop with intelligent exit detection.

Red-green-refactor loop the agent runs until tests pass.

Primitives for long-running agents: hooks and a subagent.

A ~30-line nano agent harness; bash is all you need.

Self-improving CLI agent with memory and automated skill creation.

OpenAI's built-in autonomous loop — /goal runs until the objective is met.

Drives Amp or Claude Code through a PRD task list; learnings persist in AGENTS.md.

Continuous autonomy for the Vercel AI SDK, in TypeScript.

Minimal file-based loop: fresh context, one story per iteration.

Long-running loops in parallel Docker sandboxes.

The principles behind Ralph: context, backpressure, oversight.

Curated index of Ralph implementations and writing.

Karpathy's autonomous research loop, released March 2026: give an agent one editable file, a frozen evaluator, and a scalar metric, and it runs a keep-or-revert experiment loop overnight, keeping only changes that beat the best result. The pattern has spread to prompt optimization, kernel tuning, and build-time reduction.

Claude Code's native scheduler loop (March 2026): describe a task and cadence in plain English and Claude runs it on repeat from your terminal — deploy checks, PR review, continuous tests.

Cross-agent review loop: Claude Code writes, Codex reviews, hooks manage the lifecycle until the review passes.

GitHub Next's metric-driven loop: pick a program, propose a change, evaluate, keep only if the metric improves — all state in human-readable markdown on a memory branch.

Open agent harness from HKUDS with a built-in personal agent (Ohmo) — a research-grade foundation for building your own loops.

Karpathy's autoresearch pattern packaged as an installable skill: define a goal and evaluator and let any LLM agent iterate.

Official Gemini CLI extension for Ralph loops: the agent iterates on a task, self-correcting over multiple turns without manual intervention.

Cowork's recurring-task engine is the GTM /loop: describe a workflow in plain English and it runs on a daily, weekly, or custom schedule, with file access plus CRM, email, and calendar connectors.

Anthropic's official sales plugin for Cowork: /call-prep, /pipeline-review, and /forecast commands plus auto-triggering skills for account research, competitive intelligence, and outreach drafting, wired to CRM and Outreach connectors.

Anthropic's official finance plugin for Cowork: analyze financials, build models, and track key metrics from your files and connectors.

Agent skills for sales, marketing, and GTM: CRM workflows, outbound, enrichment, note-takers, email marketing, influencer marketing, social listening, and directories.

11 SEO skills: page audits, content briefs, article writing, E-E-A-T audits, semantic gap analysis, topic clusters, and link building, with an anti-AI-slop ruleset.

GitHub's continuous-AI loops in CI/CD: scheduled agentic workflows that triage and label issues, update docs, and write reports, defined in markdown with safe outputs.

Claude Code's built-in goal loop: unlike /loop (a scheduler), /goal keeps the agent iterating until a verifiable condition holds — the native Ralph pattern with no bash required.

A long-running agent loop manager that drives OpenCode with auto-approve permissions: the agent executes, edits, and iterates without manual confirmation, supervised across iterations.

Loop-driven development with OpenCode: executes tasks from PLAN.md iteratively, each iteration in a fresh isolated session — Ralph-style context hygiene for OpenCode.

A trading-research agent loop from HKUDS: iteration budgets with a wrap-up nudge at 80 percent of budget and a forced final answer, applied to market analysis.

Karpathy's keep-or-revert autoresearch pattern rebuilt in Claude Cowork: a measurable goal, an iteration step, and keep-only-what-improves — no terminal, no code, about 7 minutes to set up.