RAGFlow is a production-grade, open-source Retrieval-Augmented Generation (RAG) engine that combines deep document understanding with agentic workflows. The system ingests heterogeneous documents (PDF, DOCX, images, web pages, etc.), parses them using a multi-stage pipeline (layout analysis, OCR, table recognition), chunks the content with various strategies (token, QA, page, etc.), indexes into vector stores (Elasticsearch, Infinity, OceanBase, SereneDB), and provides retrieval-augmented chat with LLM integration. Beyond basic RAG, it features a visual agent canvas for building complex workflows (parallel subgraphs, loops, tool calls), a sandboxed code execution environment, knowledge compilation (wiki, knowledge graphs, timelines), multi-tenant model management, and chat channel integrations (WhatsApp, Feishu, Discord). The architecture is a full-stack application with a Go backend (Gin), Python API (Flask/Quart), React/TypeScript frontend, and NATS message queue for async tasks. It is designed for enterprise deployment with Docker Compose and supports multiple LLM providers and embedding models.
This repository implements a 'Repository Harness'—a Rust-based CLI framework designed to make software codebases legible and operable for AI agents. It functions as a control plane for agent-assisted development, managing project state (stories, decisions, traces) through a combination of Git-native documents and a durable SQLite layer. The system enforces architectural rules and invariants via mechanical validation rather than process bureaucracy, distinguishing between a generic 'Core' payload and product-specific 'Consumer' work (e.g., Symphony). Key capabilities include self-updating binaries, semantic changeset replay for auditability, and explicit agent skills for onboarding and auditing. Architecturally, the codebase follows a clean separation of concerns with a Rust workspace containing `harness` (core logic) and `harness-cli` (interface). It utilizes a repository pattern to decouple business logic from database access, implementing transactional logging via JSONL changesets that support idempotent replay. The tool manages its own lifecycle through a robust installer that supports cross-platform profiles (Core vs. Core+CLI) and handles file conflicts via deterministic three-way merges. Evidence capsules and epoch fencing ensure data integrity during agent interactions and state transitions. The project demonstrates a high level of engineering maturity through its focus on reproducibility and trust boundaries. It includes extensive documentation (ADRs, execution plans, stories) and a comprehensive test suite covering installer contracts, changeset rebuilds, and boundary checks. The separation of the 'Symphony' product into a distinct repository while retaining protocol primitives in the core highlights a mature approach to library vs. application boundaries.
This repository is a meta-skill/plugin for Claude Code that serves as a 'team-architecture factory'. It is not a traditional software application but a collection of highly structured Markdown files (SKILL.md and references) that act as instructions for the Claude Code AI to design and evolve multi-agent teams. The system takes a domain description from a user and generates agent definitions, skills, and orchestrators to automate complex workflows. It demonstrates deep expertise in multi-agent orchestration: three execution modes (workflow orchestration, persistent agent collaboration, sub-agent delegation), six team architecture patterns, and workflow-native quality patterns (adversarial verification, judge panels, loop-until-dry). The project underwent a ground-up rebuild from v1 to v2 to align with the current Claude Code runtime, removing reliance on deprecated APIs like TeamCreate. The codebase is exceptionally well-documented for its domain, with clear principles, phased workflows, testing methodologies, and migration guides. The primary artifact is documentation, not executable code, which limits traditional software engineering evaluation but the craftsmanship in structuring meta-instructions for an AI is high. It is actively maintained with recent commits, thorough changelog, and professional issue templates.
AgentHub (also known as Maestro) is an Electron desktop application that orchestrates a virtual software development team of 46 AI agents powered by Claude Code CLI. The system enforces a 'Harness Engineering' methodology: Skills (standardized slash commands), Hooks (pre/post tool interceptors), Gates (quality checkpoints G0–G6), and FileWatchers (auto-sync markdown files to database). The GUI is intentionally limited to monitoring and three core operations—most workflow is driven by slash commands within Claude Code sessions. Architecture follows a three-layer pattern: Vue 3 + TypeScript renderer communicates via Electron IPC (contextBridge) to a main process with ~16 singleton services (session-manager, task-manager, gate-keeper, hook-manager, etc.). Persistence uses sql.js (SQLite in-memory) with a debounced disk save and 13 migrations. The source of truth is markdown files in `.knowledge/` and `.tasks/` directories, which are watched by chokidar and synced to the database. The app supports bilingual UI (zh-TW/en) and runs on Windows, macOS, and Linux. Key features include: sprint-based project management with task dependency tracking, interactive terminal sessions (xterm.js + node-pty), cost tracking per session, Git integration, a gate pipeline with review workflows, and a skill/hook management system with hash-based idempotent deployment. The codebase is well-structured with reusable components and services, though it shows some technical drift (alpha dependencies, brand name mismatch, Windows-specific paths) and high complexity from the extensive agent definitions and knowledge base.
This repository is an educational course on harness engineering for AI coding agents. It is a collection of lecture materials, code examples, and project templates that teach how to build environments, state management, verification, and control mechanisms for AI coding agents. The course is structured as 14 lectures and 8 projects, with a sample Electron knowledge-base app used as a running example. The repository is primarily documentation and educational content, with some reusable templates and scripts for harness creation and auditing.