R&D
LiteLLM - Providing a Unified Model API Format
· β˜• 2 min read
1. What LiteLLM Is LiteLLM is an open-source LLM adapter: call 100+ APIs (OpenAI, Anthropic, Gemini, Bedrock, Azure, Ollama, vLLM, Qwen, and more) using the standard OpenAI format. Two ways to use it: Python SDK β€” called directly from your code AI Gateway β€” a team-level proxy with authentication, billing,

CodeGraph: Helping AI Coding Assistants Understand the Codebase
· β˜• 9 min read
1. What CodeGraph Is CodeGraph is a local-first code intelligence tool. It parses a codebase with tree-sitter, stores symbols, relationships, and files in a local SQLite database, and exposes them as a queryable knowledge graph through MCP, a CLI, and a TypeScript API. Put simply, it turns “grep, glob, and Read all over the code” into an index built ahead of time, so an AI assistant can answer structural questions with just a few queries.

Superpowers: A Complete Software Engineering Methodology for AI Coding Assistants
· β˜• 5 min read
1. What Superpowers Is Superpowers is a plugin that bolts “engineering discipline” onto a coding agent, maintained by Prime Radiant. It is not a library of prompt templates but a complete software engineering methodology built on top of Skills β€” at session startup a bootstrap mechanism makes the AI automatically

OpenSpec: Align Requirements Before the AI Writes Code
· β˜• 13 min read
1. What OpenSpec Is OpenSpec is an open-source, lightweight AI-assisted spec-driven development framework. It stores specs and changes in Markdown files, drives the AI assistant with slash commands (such as /opsx:propose and /opsx:apply), and uses a CLI to manage state, validate format, and archive changes. In short, it turns “requirements talked out in a conversation” into a “traceable, iterable, archivable contract” β€” align before writing code, correct at any point during implementation, and when you are done, let the change settle into the source of truth for system behavior.

You Can Also Implement AI Agents This Way - The SOPS Edition
· β˜• 5 min read
1. Establish a SOPS Baseline SOPS stands for Standard Operating Procedures. In the production activities we carry out, there are often some basic, repetitive operational flows, and these operations are the SOPS. You need to build up a set of SOPS; by combining them you can finish tasks faster. In the past, establishing standard procedures required a senior engineer, but now with AI, producing SOPS is very easy.