Ralph Wiggum Loop
MCP serverWorker and reviewer models take turns on a coding task until the reviewer says SHIP
Runs locally- 11 tools
- Open source
- Developer tools
Worker and reviewer models take turns on a coding task until the reviewer says SHIP
Runs locally
PostScript interpreter in Rust that renders PNG, SVG and PDF, plus chalkboard math
Runs locallyCount how many AI-tagged lines survive in a git repo and log agent prompts per edit
Runs locallyLets AI agents drive a real terminal with typing, key presses, clicks and screenshots
Runs locallyHand-drawn whiteboard where Claude or ChatGPT runs a mock system design interview
Runs locallyLocal scanner that recommends MCP servers, plugins and skills for a repository
Runs locallyRead, change, test and operate SAP ABAP systems through ADT from AI coding agents
Runs locallyAnnotated screenshots for AI agents: numbered steps, arrows, boxes and solid redaction
Runs locallyIndependent checker for AI-written trading backtests: look-ahead, costs and overfitting
Runs locallyJournal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallyLets your coding agent read and resolve the review comments you leave in the Reado IDE
Runs locally
Install, launch and remote-control Minecraft Java clients and servers, headless or not
Runs locallyLets a coding agent launch Claude Code and Codex sessions that the user can watch
Runs locally
Evidence from strace, py-spy, perf, lsof and tcpdump for agents debugging live processes
Runs locallyLet Claude Code, Codex, Grok and Antigravity review each other's work
Runs locallyRead-only MCP server that finds deleted SQL Server rows in the transaction log
Runs locallyTyped, policy-checked server operations for AI agents, with approvals and an audit log
Runs locallyLocal checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands
Not checked yetInstall and administer an Epeaky encrypted-chat server over your own SSH
Runs locallyBulk domain availability checker for AI assistants, with prices at nine registrars
Runs locallyCheck your remaining Claude Code, Codex and Copilot usage limits before a long task
Runs locallyDeterministic checks of LLM answers against sources, with PASS, REVIEW or FAIL
Runs locallyInspect, search, fetch and convert local documents and mail stores with bounded access
Runs locallyMCP toolchain server to check, format, run and test programs in the Renyi language
Runs locallyLet an AI agent build, test on a device, and verify Android and iOS apps through Appium
Runs locallyPins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets
Runs locallyRead-only MCP server that lints and budgets CLAUDE.md, AGENTS.md and other steering files
Runs locallyExpose Dapr state, pub/sub, secrets, locks and actors to AI agents as MCP tools
Runs locallyCheck pages for responsive design problems and screenshot them on real device sizes
Runs locallyLocal code review of an agent's uncommitted worktree, with a 17-tool MCP server
Runs locally