Bridge between human reviewers and coding agents — annotate rendered pages in-browser and export location-aware feedback. Works with Astro, Vite, and Express.
Automated code review loop extension for pi coding agent
Local PR-review loop for human ↔ LLM. Run inside any git repo.
Orchestrates pluggable AI coding agents in an iterative plan-review loop
Two AI coding agents (Claude + GitHub Copilot) in a peer-review loop on a shared project.
Local MCP server that orchestrates an auto-review loop between a developer agent and a reviewer agent.
Automated implementation + review loop for multi-service tasks, powered by Codex Cloud and Claude.
OpenCode plugin + MCP server + skill that runs an automated GitHub Copilot PR review loop: request review, wait deterministically via `gh run watch`, triage every comment, push fixes, reply, resolve, gated merge. Solves the silent-fail of github_request_c
Agent-driven iOS Simulator control, screen streaming, gesture/keyboard input, accessibility dumps, and a self-building review loop — CLI.
Agent-driven iOS Simulator control, screen streaming, gesture/keyboard input, accessibility dumps, and a self-building review loop — CLI.
Agentic code review loop — human and agent review together
Review and fix document workflows for SPEC, PLAN, DESIGN, and COMMON documents.
AWS SDK for JavaScript Sagemaker A2i Runtime Client for Node.js, Browser and React Native
A shim for the setImmediate efficient script yielding API
npx wrapper that launches the Cascade-Bot MCP server (Python). Multi-agent Plan→Implement→Review loop for Claude Code.
High-priority task queue for Node.js and browsers
Reusable Codex/Claude Code review workflow CLI.
A local code review tool for AI-generated code. Review diffs, annotate lines, and export structured feedback that AI tools can act on.
Governed AI coding harness for pi.dev — bootstrap, plan, execute, review, and steer with deterministic policy gates
JavaScript Performance Monitor
Make Claude Code, Codex, and Gemini work properly in your Replit shell.
Pi-native Compound Engineering package for iterative development workflows
Official Compound Engineering plugin for Claude Code, Codex, and more
GitHub-issue-driven coding agent. Runs one issue at a time locally or in docker/podman sandbox mode.
A lightweight harness that keeps Claude Code working autonomously until success criteria are met. Supports any code review system (CodeRabbit, GitHub Copilot, etc.) and any CI provider. The loop: plan -> work -> check -> work -> check -> done
Generative AI-powered RFP and proposal automation for LegionIO. Ingests past proposals into Apollo, generates draft responses via LLM pipeline with RAG, and provides human-in-the-loop review workflows with analytics.