✍️Writing & Content32🎨Image Generation36🎬Video & Animation72🎵Audio & Music61💬Chatbots & Assistants49💻Coding & Development243📈Marketing & SEO79Productivity196🎯Design & UI/UX63📊Data & Analytics60📚Education & Research29💼Business & Finance71🏥Healthcare & Wellness18🔍Search & Knowledge16🤖AI Agent Infrastructure104🛡️AI Security & Testing12🧊3D & Spatial21🔎SEO Tools29🏡Real Estate4🗃️Data Extraction25🧠ADHD & Focus Tools9
Listed in Coding & Development with 246 other toolsPart of 1389+ curated AI tools on AISO
Wiggum logo

Wiggum

An open-source CLI that runs autonomous Ralph loops against your existing codebase — scan the stack, generate specs by AI interview, ship to merged PR, all on your own API keys.

freemiumThe CLI is open source and free forever: unlimited specs, all CLI commands, local execution and community support, with your own Anthropic/OpenAI keys. Paid tiers add managed API keys and monitoring rather than extra CLI capability. Pro is $19/month for 50 specs/month with an API bundle included; Pro+ is $39/month for 150 specs/month; Team is $29 per seat/month with 200 specs per seat, shared across the team, plus a team dashboard and dedicated support. All paid tiers bill $0.25 per additional spec. The web dashboard, push notifications and priority support are marked as coming soon, and the paid tiers are currently waitlist-gated.View full pricing →

Visit Wiggum

https://wiggum.app

About Wiggum

Wiggum is an open-source CLI that orchestrates the Ralph loop — an autonomous coding methodology in which an agent is given a spec and left to iterate against it unattended until the work is done — and plugs it into an existing codebase rather than a greenfield project. The workflow has three stages. Wiggum first scans your stack to build an understanding of the repository it has been pointed at. It then generates specs through an AI interview, which is the part that distinguishes it from tools that ask you to write the spec yourself: the agent asks questions about the feature until it has enough to write a spec, rather than acting on a one-line prompt. Finally it runs Ralph loops against those specs and takes the work from backlog item to merged pull request. Everything runs locally on your own API keys, which means the loop is bounded by your own provider spend rather than a vendor's credit system, and it means the code never leaves your machine. The paid tier is explicitly about visibility rather than capability: because a Ralph loop runs for a long time without supervision, the Pro plans add remote loop monitoring, a web dashboard and push notifications on completion so you are not tied to the terminal while it works.

Key Features

Ralph loop orchestration against an existing codebase, not a greenfield scaffold
Stack scan to ground the agent in the repository before it writes anything
Specs generated through an AI interview rather than a single prompt
Runs locally on your own API keys — code and spend stay yours
Backlog item to merged pull request in one unattended loop
Open-source CLI with free unlimited specs

Tags

open-sourcecliautonomous-agentsralph-loopcode-generation
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

ChatGPT already recommends Wiggum. Does it recommend yours?

If you're building in Coding & Development, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Stay updated on Coding & Development tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Agent connectivity: not yet verified