GPT-2 (2019) Paper Notes
Paper notes on GPT-2 covering its core ideas: decoder-only Transformer scaling, WebText, next-token prediction, zero-shot task transfer, and the staged release controversy.
All Posts
Dify Project Analysis: How Far Has This LLM App Platform Been Productized?
Dify is an open-source project that brings LLM app development, a workflow canvas, a RAG pipeline, model/tool plugins, MCP, and operational observability together into a single productized platform. This post analyzes its architecture through the lens of the Flask API, Graphon workflow runtime, Celery workers, Next.js console, plugin daemon, and vector backend structure.
OpenHands Project Analysis: The Boundaries of Running a Coding Agent as a Product
OpenHands productizes an AI coding agent across a local GUI, FastAPI app server, sandbox, agent-server, SDK, event store, MCP, and skill system. This analysis focuses on the boundary between the app server and GUI that the current OpenHands repository is responsible for.
Ruflo Architecture: Building an Agent Operating System on Top of Claude Code
Ruflo extends Claude Code with a CLI, MCP server, swarm coordination, AgentDB memory, hooks, background workers, a plugin marketplace, and a Web UI to create a multi-agent operations layer. This post analyzes the architecture of Ruflo — an evolution from Claude Flow — and connects it to earlier posts on agentmemory, Superpowers, and Hermes Agent.
agentmemory Architecture Analysis: Why Coding Agents Now Need a Dedicated Memory Layer
Keeping Claude Code, Codex, Gemini CLI, and OpenClaw in their own separate silos has clear limits. agentmemory collects observations via hooks, reconstructs them with BM25, vector, and graph retrieval, and creates a long-term memory layer shared across multiple agents through MCP, REST, and a viewer.