# Forward-Future/loopy

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

Repository: https://github.com/Forward-Future/loopy
Canonical: https://ross.abutalabs.com/products/loopy
Homepage: https://signals.forwardfuture.ai/loop-library/
Language: JavaScript
License: MIT
License Family: permissive
Topics: agent-skills, agentic-workflows, ai-agents, automation, codex, prompt-engineering
Last push: 2026-07-26T11:04:33+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 5
- inputs: {"age_days": 82, "days_push": 38, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3064, forks 276 (observed 2026-08-28T04:07:41.189602+00:00)

## What it is
A curated catalog of reusable AI-agent 'loops' - prompts with built-in verification, feedback, and stopping conditions - published on a browsable website with JSON and plain-text catalogs. It also ships an optional installable skill (Loopy) that guides coding agents in finding, adapting, running, and publishing these repeatable workflows.

## Use cases
- find repeatable ai agent workflows for coding tasks
- automate documentation sweeps with a coding agent
- keep a changelog up to date automatically each night
- optimize page load performance iteratively with an agent
- learn how to write agent prompts with verification and stopping conditions
- install a skill so my coding agent can find and run proven loops
- publish my own agent workflow for others to reuse

## When to choose
- you use coding agents (Codex, Claude Code, etc.) and want proven, repeatable workflows instead of one-shot prompts
- you want a browsable catalog of agent prompts with clear checks and stopping conditions
- you want to learn prompt patterns for iterative, self-verifying agent work

## When to avoid
- you need an agent runtime or orchestration framework - this is a prompt/skill catalog, not an execution engine
- you need a general-purpose agent framework with tooling, memory, or API integrations
- you want a library you can import into application code

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, agent-framework, workflow-automation, developer-tools
- domain: developer-tools, tutorials
- platform: cli
- tags: agent-skills, agentic-workflows, prompt-library, loop-library, catalog, coding-agents, ai-agents, automation, web, nodejs

## Member repositories
- Forward-Future/loopy (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.189602+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:28:17.868461+00:00, confidence not recorded.
  - readme: https://github.com/Forward-Future/loopy (fetched 2026-08-28T04:07:41.189602+00:00, sha a6a95ceef0d8)
  - homepage: https://signals.forwardfuture.ai/loop-library/ (fetched 2026-08-29T09:44:03.428520+00:00, sha c21ae7f4a60e)
  - site_page: https://signals.forwardfuture.com/loop-library/loops/overnight-docs-sweep (fetched 2026-08-29T09:44:03.440070+00:00, sha c3c13d90e066)
  - site_page: https://signals.forwardfuture.com/loop-library/loops/nightly-changelog-sweep (fetched 2026-08-29T09:44:03.442144+00:00, sha 73ba60206874)
- Data as of 2026-08-30T08:39:29.467469+00:00.