agent-pipeline

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

Ai-Agent Builder is a production-grade, "backend-less" single-file web application for authoring, configuring, and packaging AI agents. It runs entirely in the browser — no server, no API keys stored, no telemetry — making it invisible to trackers and safe for enterprise environments.

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

Vibe-coded tower-defense game built by an AI agent pipeline (planner → coder → smoke-tester → reviewer) running across Claude Code, Cursor, and VS Code Copilot.

古籍识别三 Agent 流水线：OCR → 页序重排 → 错别字纠正 | Ancient Chinese text OCR pipeline: 3-agent system for classical books, ¥0.016/page.

Reuse Agent Skills across Cursor, Claude Code, Codex, and CodeBuddy. Build task-specific AI coding agent pipelines for one project, each with an independently selected capability set.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Multi-agent pipeline simulator — planner, researcher, coder, reviewer, synthesizer tracking quality and latency

four-agent-pipeline agent skill: Specifier -> Coder -> Refactorer -> Architect. Turn a vague requirement into gate-verified code with Gherkin acceptance specs, steel-cage quality gates (coverage, complexity, duplication, mutation score), and automatic failure routing. Zero-dependency Python scaffolder included. MIT.

Your AI dev brigade for Claude Code. Multi-agent sprint pipeline with fan-out review, Bug Council, sprint learnings. Zero dependencies.

Turn a tracker ticket into a reviewed, QA-verified pull request. AI coding-agent pipeline of eight roles — plugin for Claude Code, Codex and Cursor.

Production-grade multi-agent LLM orchestration — define agents, chain them, manage state, deploy. Lightweight alternative to LangChain/CrewAI.

Overnight AI pipeline that turns live panel transcripts into responses from ten non-human and historical voices — a provotype for the World Beautiful Business Forum's AI Democracy Marathon, Athens 2026.

Orchestration system for long-running complex agent tasks

Adversarial review + provenance-audit pipeline for LLM-generated research. Catches fabrication, self-overconfidence, and data-layer inflation.

An AI agent assembly line for React Native / Expo apps — a full pipeline of specialized agents (orchestrator → architect → developer → tester → reviewer → security → release → docs) plus native Claude Code subagents. Self-contained, drop-in, config-driven.

Governed text-to-SQL analytics copilot. Claude-powered LangGraph agent scoped to certified dbt metrics. LLM cannot invent numbers that don't exist. 100% eval accuracy.

Autonomous design director — a 7-agent Gemini pipeline that plans, composes, critiques and self-corrects production-ready poster layouts from one image plus your intent. Local-first, no CSS required.

Agentic Pipeline for course creation. Mechanical verification, diagrams and house style. Highly parallel with guardrails and UI included.

Convert any site's sitemap into an Atom feed for editorial and agent pipelines