LangGenius
Dify is an LLMOps platform that helps you build GPT-based applications easily and intuitively.
Explained projects
langgenius/dify-docs: The Docs Repo That Audits Its Own Source
A Mintlify-powered documentation engine where English is canonical, translations are build artifacts, and AI-assisted rules keep the docs glued to the code.
dify-plugin-daemon: Dify Plugin Daemon turns plugin chaos into a controlled sidecar
How Dify extends its platform without letting subprocesses, Python dependencies, and runtime isolation leak into the core server.
langgenius/ruby-sdk: The SDK That Tells You to Use Something Else
A tiny Ruby client for Dify, and a bigger lesson about why AI tooling is drifting from provider-specific wrappers toward universal interfaces.
homebrew-dify: The Homebrew Tap That Behaves Like a Release Machine
A Python updater, a Ruby formula, and per-platform checksums make Dify’s CLI feel like a single command instead of a packaging project.
dify-marketplace-toolkit: The Gatekeeper Behind Dify’s Plugin Marketplace
A small Python repo that validates plugin PRs, boot-tests local installs, and hands only clean packages to Dify’s marketplace API.
dify-python-sdk: The Python client that makes Dify feel like infrastructure
A close look at the official SDK’s shared client core, typed responses, retries, and twin sync and async paths, and why that matters more than a thin wrapper should.
`langgenius/dify-official-plugins`: The Repo That Splits Dify’s Brain in Two
Models, tools, agent strategies, and data sources stop being core code and become governed extensions, with a ReAct parser that turns live model text into action.
dify-cloud-kit: Dify Cloud Kit: One Go Interface for Every Object Store
How a small abstraction layer turns S3, GCS, Azure Blob, OSS, COS, OBS, TOS, and local disk into the same developer experience.
dify-agentbox: The Docker image for agents that need to actually work
Dify AgentBox turns a polyglot, browser-ready sandbox into a reproducible build graph, so the environment is assembled from source instead of improvised by hand.
langgenius/chatbot-chrome-extension: The Smallest Possible Way to Put a Dify Bot on Every Page
A tiny Manifest V3 wrapper, a configurable iframe, and a maxed-out z-index turn one Dify app into a browser-wide assistant. The interesting work here is not intelligence. It is delivery.
Dify-Sandbox: How a Go Jail Lets LLMs Run Code Without Owning the Server
LangGenius’s sandbox trades per-task container startup for a tightly staged lock sequence: seccomp, chroot, privilege dropping, UID tricks, and a strict bootstrap order for Python and Node.js.
`langgenius/dify-plugins`: The Customs Gate for AI Plugins
A deep dive into the repo that packages, inspects, and publishes Dify extensions through a GitHub-driven marketplace pipeline.
Graphon: The Queue-Driven Engine That Makes Agent Graphs Act Like Live Systems
Inside the control loop that schedules nodes with ready queues, streams every event, and lets outside processes pause, resume, or abort a running workflow.
Inside langgenius/dify-plugin-sdks: The SDK That Lets Plugins Call Home
A Python boundary layer for manifests, transports, and reverse invocation, built so Dify plugins behave like recursive mini-agents instead of one-way add-ons.
dify-docs-archived: The docs repo that learned to police itself
Inside Dify’s archived GitBook, where bilingual docs, screenshot-heavy tutorials, and an AI-backed PR check turned documentation into infrastructure.
The Issue Tracker as a Database: Unpacking langgenius/dify-user-case
How a zero-code meta-repository uses GitHub issue templates to crowdsource production-ready LLM blueprints for the Dify ecosystem.
Escaping the Infrastructure Labyrinth: Inside dify-ee-helm-chart-values-generator
How a Python-based expert system replaces thousands of lines of manual YAML editing with an interactive, version-aware deployment pipeline.
dify-docs-mcp-server: The Great Decoupling: Inside the Dify Docs MCP Server
How a minimalist JavaScript shim turns static OpenAPI specs into a live, executable command center for AI agents.
Dify and the Rise of the LLM Engine
How a decoupled, API-first orchestration layer is replacing the "spaghetti code" of early AI agents.
Yet to be explained
mosoo
Explain
The open-source Agent Gallery and Gateway for Codex, Claude Agent SDK, and OpenCode. Developers publish an Agent once behind one HTTP API; users run it in an isolated cloud sandbox—no local harness setup, compute, or runtime infrastructure.
mosoo-agent-driver
Explain
Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).
mosoo-connector
Explain
AI agent CLI and coding-agent Skill for mosoo. Configure, publish, run, and inspect agents through the Agent API on cloud, local, or self-hosted targets.
mosoo-docs
Explain
Product and API documentation for the mosoo open-source agent runtime for coding agents.
mosoo-website
Explain
Landing page; Blog; Api reference; etc.
mosoo-skills
Explain
Reusable, project-aware coding-agent skills for mosoo.
dify-go-sdk
Explain
Go SDK for Dify: run apps, manage knowledge bases, and deploy through the console API
tokener-cli
Explain
Tokener.ai command-line tool, generated from the Console Management API spec with lathe.
dify-ee-terraform-aws
Explain
Deploy Dify EE in your AWS
dify-test-infra
Explain
Shared CI test timing statistics and maintenance workflows for Dify